© 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. 31367
    Prev
    Next
    INDEX
    Explanations

    Dalaca, Ptyoiulus, Bank names

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

    The neuron is selectively activating on numeric tokens (i.e. numbers, especially multi‐digit years or codes).

    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
    providedIn
    -1.06
     but
    -0.92
    玉石
    -0.87
    ditionally
    -0.86
    ecx
    -0.86
    ̶
    -0.86
    ();)
    -0.84
    🛠
    -0.84
    〖
    -0.84
     layui
    -0.83
    POSITIVE LOGITS
    これも
    0.98
     poate
    0.93
    Bland
    0.92
    niaus
    0.92
    也沒有
    0.88
     erforderlichen
    0.88
    luß
    0.88
     могу
    0.85
    也沒
    0.85
     Bland
    0.85
    Activations Density 0.007%

    No Known Activations