© 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. 22-GEMMASCOPE-RES-131K
    7. 72056
    Prev
    Next
    INDEX
    Explanations

    importance and severity

    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_22/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
    
    -1.48
     naviguant
    -1.47
     estadounid
    -1.45
     célè
    -1.42
     tranſ
    -1.41
    quelles
    -1.40
    giques
    -1.40
     bolsillos
    -1.38
    뻣
    -1.38
     pérd
    -1.36
    POSITIVE LOGITS
     when
    1.76
     important
    1.55
     cuando
    1.52
     for
    1.48
     notable
    1.44
     F
    1.41
    A
    1.40
     L
    1.38
    An
    1.38
    L
    1.36
    Activations Density 0.039%

    No Known Activations