© 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. 96625
    Prev
    Next
    INDEX
    Explanations

    from even/every

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

    hands, patient

    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
    u
    0.46
     উন্নয়ন
    0.42
     COULD
    0.42
    𒉣
    0.41
     ضرورت
    0.41
     Irene
    0.40
     RULES
    0.40
    ღ
    0.40
    basis
    0.39
     наверное
    0.39
    POSITIVE LOGITS
    ewidth
    0.47
    }->
    0.47
    НЯ
    0.47
    ')->
    0.45
    ése
    0.44
    ookeeper
    0.44
    द्व
    0.42
    hoff
    0.41
    ملك
    0.41
    MODKEY
    0.41
    Activations Density 0.000%

    No Known Activations