© 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. 31396
    Prev
    Next
    INDEX
    Explanations

    separator or boundary

    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
    værk
    -0.90
    涯
    -0.88
     jų
    -0.83
     كري
    -0.83
    boundary
    -0.83
     mojej
    -0.83
     dobré
    -0.83
    пле
    -0.82
    besch
    -0.82
    ']>;
    -0.82
    POSITIVE LOGITS
     between
    1.13
    ight
    0.94
    less
    0.88
    ători
    0.87
     ubic
    0.85
     leb
    0.85
     Ubic
    0.84
    tween
    0.83
     Disse
    0.81
    舔
    0.80
    Activations Density 0.014%

    No Known Activations