© 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. 58938
    Prev
    Next
    INDEX
    Explanations

    Khaminets; naive

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

    LitRPG

    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
     облі
    0.50
     отрица
    0.49
     संथाल
    0.47
    ﺒ
    0.45
     manifestazione
    0.44
    ıc
    0.44
    ">(</
    0.44
    บัญ
    0.44
    дка
    0.43
     manglid
    0.43
    POSITIVE LOGITS
    на
    0.57
    나
    0.53
    な
    0.50
     Kahn
    0.49
    noy
    0.49
    nais
    0.46
    naive
    0.45
    вої
    0.44
    na
    0.43
     Investigations
    0.43
    Activations Density 0.000%

    No Known Activations