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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91258
    Prev
    Next
    INDEX
    Explanations

    platform developer system OS

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

    The neuron strongly activates on numeric tokens (multi‐digit numbers, version numbers, file‐path digits, etc.), i.e. it detects sequences of digits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    сан
    -0.83
     kveld
    -0.76
     Интернет
    -0.72
     Sana
    -0.70
    ｳ
    -0.70
     paar
    -0.70
    ホルモン
    -0.70
    inama
    -0.70
     Pense
    -0.70
    née
    -0.69
    POSITIVE LOGITS
    ený
    0.78
     thus
    0.76
     Platform
    0.75
    텐츠
    0.75
     thats
    0.73
    Platform
    0.73
    znamu
    0.73
    Xor
    0.73
    TEP
    0.73
    iosa
    0.70
    Activations Density 0.032%

    No Known Activations