© 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. 52198
    Prev
    Next
    INDEX
    Explanations

    business and system concepts

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

    `Activity` `Issues` `cluster` `store`

    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
     satu
    0.48
     csak
    0.48
    ﾕ
    0.46
     ĝi
    0.46
     stvar
    0.46
     nir
    0.45
     chercheurs
    0.44
     جه
    0.44
     viva
    0.44
     jedan
    0.44
    POSITIVE LOGITS
    aurus
    0.39
     Roblox
    0.38
    ぐるみ
    0.37
    ↵↵↵
    0.37
    Preg
    0.37
    distinct
    0.36
    ";
    0.36
    Profile
    0.36
    Camel
    0.36
    ཁ
    0.36
    Activations Density 0.000%

    No Known Activations