© 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. 69508
    Prev
    Next
    INDEX
    Explanations

    in shorthowcity.knownensure

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

    engine isn't

    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
    🖊
    0.50
     específicamente
    0.49
     नमक
    0.48
     automáticamente
    0.47
     เกี่ยว
    0.46
    gång
    0.46
    ेश्च
    0.45
    íts
    0.45
    휋
    0.45
     código
    0.44
    POSITIVE LOGITS
    u
    0.59
    s
    0.50
    derived
    0.49
    v
    0.48
    w
    0.47
    <0x0D>
    0.47
     perfused
    0.47
    extract
    0.45
    d
    0.45
    r
    0.45
    Activations Density 0.006%

    No Known Activations