© 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. 64897
    Prev
    Next
    INDEX
    Explanations

    programming method calls and properties

    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
     chamado
    -1.34
    に入れる
    -1.33
     magnificent
    -1.32
     probabilmente
    -1.23
     goddamn
    -1.22
     crucial
    -1.21
     cucchiaio
    -1.21
    ///</
    -1.20
     focuses
    -1.20
    に入れ
    -1.20
    POSITIVE LOGITS
     or
    1.63
     if
    1.41
     Desember
    1.41
     after
    1.34
     before
    1.32
    dienne
    1.31
     in
    1.30
    razine
    1.30
     because
    1.24
    灵气
    1.22
    Activations Density 0.291%

    No Known Activations