© 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. 61092
    Prev
    Next
    INDEX
    Explanations

    bits enables

    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
    ě
    0.45
    ismus
    0.45
    bigl
    0.44
     tartış
    0.42
     poema
    0.42
     contrasted
    0.41
     inconven
    0.40
    ními
    0.40
     emphatic
    0.40
    gehend
    0.39
    POSITIVE LOGITS
    萊
    0.52
     Doha
    0.41
    咉
    0.41
     जीबी
    0.41
     همراه
    0.39
     নির্মিত
    0.39
     DOF
    0.39
    方を
    0.38
    ⼤
    0.38
    شک
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.