© 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. 22-GEMMASCOPE-RES-131K
    7. 35405
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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
     zwykle
    -1.24
     обычно
    -1.15
     in
    -1.11
    なんですね
    -1.09
    antastic
    -1.09
     where
    -1.09
     Ausblick
    -1.09
    に於
    -1.08
     близько
    -1.08
     doskona
    -1.06
    POSITIVE LOGITS
     ""
    1.42
    𝐻
    1.24
     ヶ
    1.20
     سایر
    1.19
     castillo
    1.18
     autres
    1.17
    ֠
    1.16
    האם
    1.16
    quelize
    1.13
     château
    1.13
    Activations Density 0.003%

    No Known Activations