© 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. 163926
    Prev
    Next
    INDEX
    Explanations

    We always

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

    descriptive nouns and adjectives

    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
    رم
    0.53
    C
    0.52
    Help
    0.49
    ри
    0.48
     janeiro
    0.48
    simplified
    0.47
     streamline
    0.46
    M
    0.46
    LIGHT
    0.45
    N
    0.44
    POSITIVE LOGITS
     lähe
    0.45
     attacking
    0.44
    azie
    0.43
    كية
    0.42
    গামী
    0.41
     tellement
    0.40
     এইসব
    0.40
     Brant
    0.39
    葙
    0.39
    urring
    0.38
    Activations Density 0.000%

    No Known Activations