© 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. 10-GEMMASCOPE-RES-131K
    7. 71898
    Prev
    Next
    INDEX
    Explanations

    reading text or code

    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_10/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
    ’
    -3.73
    ing
    -3.02
    m
    -2.86
    ?"
    -2.84
    y
    -2.84
    u
    -2.75
    ですので
    -2.66
    k
    -2.56
     they
    -2.48
    ho
    -2.45
    POSITIVE LOGITS
    ꯶
    2.98
    
    2.91
    猡
    2.91
     schönes
    2.81
    jaqueta
    2.72
     italie
    2.69
    pulseira
    2.66
    unjungi
    2.63
     spørsmål
    2.63
    ꯸
    2.55
    Activations Density 0.040%

    No Known Activations