© 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. 107128
    Prev
    Next
    INDEX
    Explanations

    `is a`

    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
     Langen
    -0.81
     uomini
    -0.77
    cols
    -0.75
    Jeffrey
    -0.74
    Mot
    -0.72
    themes
    -0.71
    合成
    -0.71
    ombre
    -0.71
    Ahmad
    -0.69
     Johansson
    -0.69
    POSITIVE LOGITS
    riever
    0.69
     apprehend
    0.67
     overcrow
    0.66
    æk
    0.65
     concurs
    0.64
    道歉
    0.63
    autés
    0.63
    醫生
    0.63
     ברי
    0.62
    ultural
    0.60
    Activations Density 0.115%

    No Known Activations