© 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. 249371
    Prev
    Next
    INDEX
    Explanations

    of the, of the, than the, triggered the, States vote, tournament, chassis management

    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
    AND
    0.62
    antes
    0.53
    áš
    0.51
    ৫
    0.49
    exclusion
    0.47
    órico
    0.46
    𝕀
    0.46
    OT
    0.46
    TC
    0.46
    symbol
    0.46
    POSITIVE LOGITS
     faulted
    0.46
    કસ
    0.44
     предпо
    0.43
     anal
    0.42
     ObjectMapper
    0.42
     Sequel
    0.42
     Autof
    0.42
     Tief
    0.42
     lingua
    0.41
     gesetzt
    0.41
    Activations Density 0.000%

    No Known Activations