© 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. 170184
    Prev
    Next
    INDEX
    Explanations

    sales, focused, recorded, art

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

    surprisingly complex

    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
    дары
    0.41
     географи
    0.41
    =${
    0.39
     системы
    0.39
     ਹੈ
    0.38
     درجه
    0.38
     జరిగింది
    0.38
    disamb
    0.37
    अनुसूचित
    0.37
     sizeof
    0.37
    POSITIVE LOGITS
    洮
    0.49
     emanc
    0.48
     Aank
    0.47
     avance
    0.46
    lado
    0.46
     Rukh
    0.46
    رے
    0.46
     बचा
    0.45
    ិត្ត
    0.45
    رائی
    0.45
    Activations Density 0.000%

    No Known Activations