© 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. 15752
    Prev
    Next
    INDEX
    Explanations

    left, right, three, positive, open

    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
    fpm
    -0.81
     basée
    -0.78
    jmp
    -0.77
     Texte
    -0.76
    know
    -0.75
    rão
    -0.74
     Theologie
    -0.74
    銚
    -0.73
     pasirink
    -0.73
     مدير
    -0.71
    POSITIVE LOGITS
     Brut
    0.86
     verksamhet
    0.85
     другом
    0.85
     gari
    0.82
     another
    0.80
     liebe
    0.78
    deserved
    0.77
    ֱ
    0.77
     mussels
    0.77
    כר
    0.77
    Activations Density 0.389%

    No Known Activations