© 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. 134326
    Prev
    Next
    INDEX
    Explanations

    lists and information

    np_acts-logits-general · gemini-2.5-flash-lite

    lists of common phrases

    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
    ud
    0.69
    顓
    0.48
     கும்ப
    0.48
    ub
    0.47
    udian
    0.46
     усилия
    0.46
    ça
    0.46
    ура
    0.45
    (:,
    0.45
    çek
    0.45
    POSITIVE LOGITS
     algorithms
    0.53
    MO
    0.47
     doctora
    0.46
     carbon
    0.44
     ambulance
    0.44
     cultures
    0.44
     doet
    0.44
     immobilier
    0.44
     algorithm
    0.43
     actriz
    0.42
    Activations Density 0.000%

    No Known Activations