© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66334
    Prev
    Next
    INDEX
    Explanations

    Ras

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "Ras" which appears to be related to proteins and biochemical pathways in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron never reliably activates on any recurring token pattern—it appears to be effectively “dead” and doesn’t detect any consistent feature.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]
    -3.05
    𐄙
    -2.92
    !”
    -2.36
     provides
    -2.14
    镦
    -2.11
    ]]=
    -2.11
     stringent
    -2.11
     circunstancias
    -2.09
    蒾
    -2.08
    )।
    -2.06
    POSITIVE LOGITS
    er
    3.23
    o
    2.80
    and
    2.48
    E
    2.41
    あります
    2.28
     delantera
    2.22
     eds
    2.19
    ft
    2.16
    of
    2.14
     حين
    2.14
    Activations Density 0.004%

    No Known Activations