© 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. 73450
    Prev
    Next
    INDEX
    Explanations

    copyright and actions

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

    details, functions, personnel

    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
     κατο
    0.48
     непосредственно
    0.48
    ósfera
    0.47
     acompañ
    0.45
    anki
    0.45
    .
    0.44
     anderen
    0.43
     фактически
    0.43
    ти
    0.42
    тика
    0.42
    POSITIVE LOGITS
     경우에는
    0.49
     경우는
    0.46
    暘
    0.46
    پے
    0.43
    বিত্র
    0.43
     Dunne
    0.43
    फेक्शन
    0.42
    ParallelGroup
    0.42
     소녀
    0.42
    𒀊
    0.42
    Activations Density 0.000%

    No Known Activations