© 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. 89469
    Prev
    Next
    INDEX
    Explanations

    or, which

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

    getter or identifier

    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
    感じる
    0.46
     پیم
    0.45
    あった
    0.44
    猜
    0.43
    ब्रे
    0.43
    ابه
    0.43
     parallèle
    0.43
    ありました
    0.43
     किन्तु
    0.42
    भर
    0.42
    POSITIVE LOGITS
    icherheit
    0.49
    ClFN
    0.49
    甾
    0.49
     Elytres
    0.48
     steroid
    0.48
     luật
    0.47
    বায়
    0.47
     unbear
    0.46
     screened
    0.46
    மணிய
    0.45
    Activations Density 0.001%

    No Known Activations