© 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. 46160
    Prev
    Next
    INDEX
    Explanations

    has since, guys live, which means

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

    comma-separated lists, parameters

    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
    ي
    0.61
    า
    0.56
    ब्राह
    0.51
    caution
    0.49
    解锁
    0.47
    drivers
    0.46
    ी
    0.45
     जो
    0.45
    ி
    0.45
    色の
    0.45
    POSITIVE LOGITS
    Filed
    0.46
    ChatMessage
    0.46
     tril
    0.45
    (
    0.45
     software
    0.43
    MediaProfile
    0.43
    Fax
    0.43
     lateral
    0.43
     nél
    0.43
    Parameterized
    0.43
    Activations Density 0.001%

    No Known Activations