© 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. 26785
    Prev
    Next
    INDEX
    Explanations

    code with various languages

    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
    providedIn
    -1.96
    the
    -1.55
    what
    -1.48
    why
    -1.37
    ２
    -1.34
    ５
    -1.29
    了一会儿
    -1.29
    ３
    -1.25
     Königreich
    -1.24
    唏
    -1.23
    POSITIVE LOGITS
     gäng
    1.74
     größe
    1.59
     tatsäch
    1.45
    twas
    1.36
     usado
    1.34
    為に
    1.34
     ständig
    1.32
     scarpe
    1.31
     gän
    1.31
     wielu
    1.28
    Activations Density 0.004%

    No Known Activations