© 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. 31338
    Prev
    Next
    INDEX
    Explanations

    whole family

    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
     it
    -0.88
     an
    -0.85
     Wednesday
    -0.79
     Tuesday
    -0.78
     a
    -0.74
     Sir
    -0.72
    ite
    -0.71
    M
    -0.70
    тивний
    -0.70
    基
    -0.69
    POSITIVE LOGITS
     family
    2.55
     خانواده
    1.86
     keluarga
    1.82
     the
    1.80
    family
    1.78
     famiglia
    1.77
     famille
    1.63
     familien
    1.63
     Familie
    1.54
     família
    1.54
    Activations Density 0.051%

    No Known Activations