© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19148
    Prev
    Next
    INDEX
    Explanations

    domain endings and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    См
    0.42
    CHREIB
    0.40
    ُونَ
    0.38
    鮋
    0.38
     ಪ
    0.37
    。《
    0.37
    Ⲛ
    0.37
     selfishness
    0.36
    क्लेव
    0.36
    }$&$-
    0.35
    POSITIVE LOGITS
    ,
    0.55
    /
    0.45
    ',
    0.44
    ’,
    0.43
    ",
    0.40
    ”,
    0.40
     Berg
    0.40
     Allen
    0.39
    ;
    0.38
     glacial
    0.37
    Activations Density 0.000%

    No Known Activations