© 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. 7982
    Prev
    Next
    INDEX
    Explanations

    dimensions, serial numbers, code or names

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

    letters followed by punctuation or slash

    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
    renzia
    0.37
    HARAD
    0.36
    okatokat
    0.34
    াইয়৷
    0.34
     ɖ
    0.34
    癃
    0.34
    )،
    0.32
     skapa
    0.32
    HOBBIT
    0.32
    <unused40>
    0.31
    POSITIVE LOGITS
    i
    0.48
    0.46
    that
    0.44
    if
    0.41
    we
    0.40
    c
    0.39
    t
    0.38
    p
    0.38
     that
    0.37
    e
    0.36
    Activations Density 0.528%

    No Known Activations