© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51236
    Prev
    Next
    INDEX
    Explanations

    distinct characteristics and effects

    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_65k_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
    ᱖
    0.52
    ೊಳ್ಳ
    0.49
    ளிக்க
    0.48
    ියා
    0.47
    늉
    0.46
    ్యాచ్
    0.46
    境界層
    0.46
     sulfonic
    0.46
    ాలు
    0.46
    ილები
    0.45
    POSITIVE LOGITS
    Mac
    0.52
    us
    0.49
    Message
    0.49
    ON
    0.47
     MAC
    0.47
    MAC
    0.46
    St
    0.46
    riere
    0.46
    2
    0.46
    ulus
    0.46
    Activations Density 0.003%

    No Known Activations