© 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. 17455
    Prev
    Next
    INDEX
    Explanations

    various grammatical structures

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

    numbers and abstract concepts

    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
    X
    0.41
    R
    0.39
    on
    0.39
    W
    0.39
    i
    0.38
     "\(
    0.38
    as
    0.36
     R
    0.36
    Z
    0.36
    oa
    0.35
    POSITIVE LOGITS
     joyous
    0.42
     murderous
    0.37
    가는
    0.36
     schizophren
    0.35
    direccion
    0.35
     incite
    0.35
     ngunit
    0.35
     ਨੂੰ
    0.34
     повин
    0.34
    ѕ
    0.34
    Activations Density 0.134%

    No Known Activations