© 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. 96632
    Prev
    Next
    INDEX
    Explanations

    situations should

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

    explaining conditions or dependencies

    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
     CRUZ
    0.46
     responsabile
    0.44
     independente
    0.43
     indépend
    0.43
     trži
    0.43
     dirigeants
    0.42
     gouver
    0.42
    吏
    0.42
     líder
    0.41
    いたり
    0.41
    POSITIVE LOGITS
    өг
    0.45
    мо
    0.45
    =-
    0.44
    $,
    0.42
    Simplify
    0.42
     రూప
    0.42
     నాలుగు
    0.42
    ху
    0.42
     투
    0.42
     वार्
    0.42
    Activations Density 0.001%

    No Known Activations