© 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. 146052
    Prev
    Next
    INDEX
    Explanations

    annual report photographer

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

    suggests or represents

    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
     potenti
    0.53
     interfere
    0.49
    }}
    0.48
     Nerd
    0.47
     afgelopen
    0.47
     interfering
    0.47
     reiterate
    0.46
     fortfarande
    0.46
     solvation
    0.46
     interrom
    0.46
    POSITIVE LOGITS
    не
    0.55
    w
    0.55
    пара
    0.53
    OP
    0.48
    incl
    0.47
    ┝
    0.46
    mujer
    0.46
    igned
    0.46
    DISTANCE
    0.46
    ON
    0.45
    Activations Density 0.000%

    No Known Activations