© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99501
    Prev
    Next
    INDEX
    Explanations

    going to

    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
    quay
    -0.89
    opard
    -0.75
    eldo
    -0.75
     './../
    -0.74
     ditetapkan
    -0.73
    sour
    -0.73
     racing
    -0.72
    guero
    -0.72
    ngdoc
    -0.70
    porta
    -0.69
    POSITIVE LOGITS
    トロ
    0.85
     Seat
    0.81
     crops
    0.76
     Walk
    0.75
    ἑ
    0.74
     walk
    0.73
     Crops
    0.72
    Walk
    0.72
     θ
    0.70
    inction
    0.69
    Activations Density 0.010%

    No Known Activations