© 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. 218390
    Prev
    Next
    INDEX
    Explanations

    python code imports and modules

    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
     dragState
    0.42
    ப்ச
    0.42
     клави
    0.40
     abnormally
    0.39
     shrunk
    0.39
     unusually
    0.38
     rotated
    0.38
    ણ
    0.38
    lecht
    0.38
     overlapped
    0.38
    POSITIVE LOGITS
     Implementation
    0.44
     Const
    0.42
     Hari
    0.42
     Hatteras
    0.42
     Learning
    0.42
    而来
    0.41
     on
    0.41
    usi
    0.40
     March
    0.40
     Feb
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.