© 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. 34432
    Prev
    Next
    INDEX
    Explanations

    onto the

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

    react, svelte code blocks

    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
     краю
    0.45
     버튼
    0.42
    찹
    0.42
    畢業
    0.41
    钮
    0.41
    方向
    0.40
    年会
    0.40
    ButtonPressed
    0.40
    )<-
    0.40
    萝
    0.40
    POSITIVE LOGITS
     *,
    0.47
    ☯
    0.47
     dets
    0.45
     Aq
    0.44
     provider
    0.43
     pouls
    0.42
     निर्देशक
    0.41
     Provider
    0.41
     who
    0.40
    omnia
    0.40
    Activations Density 0.000%

    No Known Activations