© 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. 115991
    Prev
    Next
    INDEX
    Explanations

    bookmarked it

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

    categorization and explanation

    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
    ᱧ
    0.49
     bajos
    0.47
    mipmap
    0.46
     soạn
    0.45
     ай
    0.44
    手里
    0.44
     gastronomy
    0.44
    竦
    0.44
     budgets
    0.43
     magg
    0.43
    POSITIVE LOGITS
    Defining
    0.45
    Objective
    0.42
     Objective
    0.42
     Nicht
    0.41
     Dunne
    0.41
    "};
    0.41
     Subscription
    0.41
     Webber
    0.41
    Expl
    0.40
     ойнотуу
    0.40
    Activations Density 0.002%

    No Known Activations