© 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. 7493
    Prev
    Next
    INDEX
    Explanations

    initial state or value

    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
     through
    -1.63
    <
    -1.49
     then
    -1.43
     &
    -1.42
            
    -1.41
     \&
    -1.36
     during
    -1.34
    %
    -1.30
     thru
    -1.30
     directly
    -1.29
    POSITIVE LOGITS
    KeyType
    1.41
    paket
    1.41
    しておく
    1.35
    ⿵
    1.35
     jednej
    1.34
    soby
    1.34
    saya
    1.34
    戗
    1.33
    posisi
    1.33
    JOR
    1.30
    Activations Density 0.070%

    No Known Activations