© 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. 34-GEMMASCOPE-RES-131K
    7. 58401
    Prev
    Next
    INDEX
    Explanations

    android id attributes

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

    This neuron responds to sequences of non-Latin characters (notably Arabic script).

    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
     now
    -0.86
    などを
    -0.82
     some
    -0.81
    を
    -0.81
    互動
    -0.79
    <0xA3>
    -0.77
    ？』
    -0.76
    見て
    -0.74
     do
    -0.73
     have
    -0.73
    POSITIVE LOGITS
    TimeoutException
    1.03
    criminal
    0.97
    busters
    0.94
    werke
    0.93
    isque
    0.90
    Statistics
    0.90
     sunrise
    0.89
    歘
    0.88
    coaster
    0.87
     droite
    0.86
    Activations Density 0.007%

    No Known Activations