© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68163
    Prev
    Next
    INDEX
    Explanations

    Bufonidae toads

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

    numerical values with negative signs, particularly in mathematical notation and code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    北部
    -2.41
    ]
    -2.25
     &
    -2.19
    ly
    -2.17
    ・・・。
    -2.16
    二百
    -2.09
     from
    -2.08
    *
    -2.08
    ❋
    -2.06
    れている
    -2.03
    POSITIVE LOGITS
    珵
    2.81
    嵛
    2.66
    𖣘
    2.56
    跻
    2.55
     fidé
    2.55
    仨
    2.53
    薷
    2.52
    ︲
    2.52
     opulent
    2.48
    3
    2.47
    Activations Density 0.007%

    No Known Activations