© 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. 35230
    Prev
    Next
    INDEX
    Explanations

    evaluation and percentages

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

    subjective scores and evaluations

    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
     самом
    0.47
     изменить
    0.46
     interact
    0.46
     Fehl
    0.46
     شويه
    0.46
     unre
    0.45
     ሁ
    0.44
    шымта
    0.44
     juega
    0.44
     novices
    0.44
    POSITIVE LOGITS
    evaluated
    0.49
    total
    0.46
    評價
    0.44
    ?,
    0.43
    ריה
    0.43
    evaluation
    0.43
    customer
    0.43
    to
    0.42
    iapkan
    0.41
    "
    0.41
    Activations Density 0.000%

    No Known Activations