© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137434
    Prev
    Next
    INDEX
    Explanations

    generalization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     поба
    0.46
     Résultats
    0.43
     официально
    0.43
    人间
    0.43
     ụ
    0.43
    ůj
    0.42
     услуг
    0.42
     juillet
    0.41
     гле
    0.41
     commitments
    0.41
    POSITIVE LOGITS
    G
    0.56
    Circ
    0.51
    Method
    0.47
    Lit
    0.47
    Mit
    0.47
    AY
    0.46
    Q
    0.45
    circ
    0.44
    im
    0.44
    Mode
    0.44
    Activations Density 0.003%

    No Known Activations