© 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. 110117
    Prev
    Next
    INDEX
    Explanations

    descriptive product/content phrases

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

    content moderation requests

    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
    iments
    0.44
    ahanglan
    0.44
    Benzo
    0.44
     उच्चतम
    0.43
    äg
    0.42
     Bracket
    0.42
    ୦
    0.42
     Braunschweig
    0.41
    唑
    0.41
     Rü
    0.41
    POSITIVE LOGITS
    的作品
    0.46
     مذہ
    0.41
     HAY
    0.41
     作品
    0.39
     january
    0.38
     produits
    0.38
     contenus
    0.38
     february
    0.38
     작품
    0.37
     tuổi
    0.37
    Activations Density 0.002%

    No Known Activations