© 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. 129099
    Prev
    Next
    INDEX
    Explanations

    code syntax delimiter

    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
     电脑
    -0.98
    Composable
    -0.96
    icare
    -0.94
    SFER
    -0.93
    itoriale
    -0.90
     desafios
    -0.88
     estuvieron
    -0.85
     安卓
    -0.85
     托
    -0.84
    ifon
    -0.82
    POSITIVE LOGITS
     OGSÅ
    0.90
     maintenant
    0.85
     şimdi
    0.83
    kezett
    0.82
    })();
    0.82
     riemp
    0.82
     qualcosa
    0.82
    Цена
    0.81
    klara
    0.81
     municipio
    0.81
    Activations Density 0.006%

    No Known Activations