© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111830
    Prev
    Next
    INDEX
    Explanations

    H followed by sequence

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

    This neuron activates on numeric tokens, detecting standalone numbers (including integers, decimals, and negative values).

    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
    .”
    -2.38
    u
    -2.34
    شما
    -2.31
     guerrero
    -2.28
    </h3>
    -2.25
     feitas
    -2.19
    以上です
    -2.13
    )
    -2.06
     эффектив
    -2.06
    i
    -2.03
    POSITIVE LOGITS
    UAWEI
    2.22
    去
    2.13
     essentials
    2.09
    9
    2.08
    </b>
    2.08
    рую
    2.05
     pudiera
    1.97
    
    1.91
     tuviera
    1.90
    会在
    1.89
    Activations Density 0.317%

    No Known Activations