© 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. 65649
    Prev
    Next
    INDEX
    Explanations

    code and localization strings

    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
    -
    -1.12
     on
    -1.08
    новые
    -1.05
    новая
    -1.03
    -/
    -1.02
    👾
    -1.02
     in
    -0.98
    Inoltre
    -0.97
     Polícia
    -0.95
    vier
    -0.94
    POSITIVE LOGITS
    這些
    1.12
     Ausführungen
    1.00
    これらの
    0.98
     всегда
    0.97
     Betrach
    0.97
     Bereiche
    0.97
    lihat
    0.96
    Mitar
    0.93
    这两
    0.93
    Noten
    0.92
    Activations Density 0.012%

    No Known Activations