© 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. 107926
    Prev
    Next
    INDEX
    Explanations

    small followed by noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     konflik
    -0.77
     verke
    -0.77
    lary
    -0.75
     hemoglobin
    -0.75
    SCO
    -0.75
     jene
    -0.72
    zette
    -0.72
     koste
    -0.71
     rechter
    -0.71
    级
    -0.71
    POSITIVE LOGITS
     Small
    1.09
     Large
    0.82
    wares
    0.81
     large
    0.77
    Mensaje
    0.77
    Small
    0.77
    ternos
    0.76
    ណ
    0.75
     décédé
    0.75
    ensión
    0.74
    Activations Density 0.048%

    No Known Activations