© 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. 13686
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

    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
    UTHER
    0.42
     coexistence
    0.39
     внутріш
    0.38
     зна
    0.38
    𝘢
    0.38
     INTERNAL
    0.37
     мо
    0.36
     неде
    0.36
     возмо
    0.35
     YO
    0.35
    POSITIVE LOGITS
    ྤ
    0.43
     persuade
    0.40
    Grun
    0.40
    ོན་
    0.39
     Town
    0.39
    Town
    0.39
    пс
    0.39
    町
    0.39
     લાભ
    0.38
    ቖ
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.