© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56924
    Prev
    Next
    INDEX
    Explanations

    Retro Blonde

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

    The neuron primarily detects numeric tokens (digits and numbers) in mathematical or data‐driven contexts.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    যোগ
    -0.77
    illa
    -0.74
     diode
    -0.73
    fizierung
    -0.73
     Viene
    -0.68
     officially
    -0.67
    原則
    -0.66
    DisplayMetrics
    -0.66
     anticor
    -0.66
    OPINION
    -0.65
    POSITIVE LOGITS
    prong
    0.84
     conjug
    0.82
    Moved
    0.82
     Conjug
    0.79
    disse
    0.79
    Dade
    0.77
     Dade
    0.77
     típicos
    0.77
     Embedding
    0.76
    辅导
    0.76
    Activations Density 0.067%

    No Known Activations