© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37255
    Prev
    Next
    INDEX
    Explanations

    code reformatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ）・
    0.53
    VILLE
    0.50
    َى
    0.50
     ivvu
    0.49
     تغيير
    0.48
     schimb
    0.47
    OLYBD
    0.47
    ਰ
    0.46
     restaurantes
    0.46
     vías
    0.45
    POSITIVE LOGITS
    formula
    0.47
    form
    0.45
    reson
    0.45
    drift
    0.43
    Haven
    0.43
    equivalent
    0.43
    ome
    0.42
    elty
    0.42
    这话
    0.42
    ash
    0.41
    Activations Density 0.000%

    No Known Activations