© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79599
    Prev
    Next
    INDEX
    Explanations

    new version or model

    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
     Vereinigten
    -1.29
    線が
    -1.19
    panou
    -1.19
     large
    -1.17
    xlarge
    -1.12
     Situationen
    -1.12
     maravillas
    -1.11
     своим
    -1.10
     jsem
    -1.09
    tispiece
    -1.09
    POSITIVE LOGITS
     friv
    1.32
     salat
    1.22
    quilo
    1.22
     kasa
    1.21
     kazak
    1.20
     COMPUTER
    1.20
     beren
    1.20
    usura
    1.20
     グリル
    1.20
     eier
    1.19
    Activations Density 0.026%

    No Known Activations