© 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. 123154
    Prev
    Next
    INDEX
    Explanations

    production readiness and existing customers

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

    without consuming or revealing

    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
     diretto
    0.46
    odas
    0.45
    britann
    0.44
    deviation
    0.43
     finiteness
    0.43
     POLICY
    0.42
    bung
    0.41
    ۵
    0.41
     svega
    0.40
    communications
    0.40
    POSITIVE LOGITS
     постепенно
    0.49
    LuaPush
    0.45
    ன்
    0.45
     startTime
    0.45
     مشر
    0.45
     પ્રથમ
    0.45
     стадии
    0.45
    fireFlower
    0.44
     деп
    0.44
     ምልክ
    0.44
    Activations Density 0.002%

    No Known Activations