© 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. 11786
    Prev
    Next
    INDEX
    Explanations

    compiled code and logging

    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
    谣
    0.44
    ianSpace
    0.43
    ಿದ್ದೇನೆ
    0.42
    婹
    0.42
     нәрсә
    0.41
    ினேன்
    0.41
     Coulter
    0.40
    䢁
    0.39
    avkh
    0.39
     уены
    0.39
    POSITIVE LOGITS
    JAVA
    0.41
    0.41
    }
    0.41
    Java
    0.40
    extension
    0.40
    dru
    0.39
    *
    0.39
    ri
    0.39
    long
    0.39
    这时
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.