© 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. 53233
    Prev
    Next
    INDEX
    Explanations

    standard deviation, lug nuts

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

    flow rates, leads, startups, research

    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
    n
    0.63
    vase
    0.54
    inek
    0.53
    semblance
    0.50
     sembl
    0.50
    ist
    0.50
    b
    0.49
    inj
    0.48
    g
    0.47
    zun
    0.47
    POSITIVE LOGITS
     Orioles
    0.47
     thí
    0.45
     Tiến
    0.43
     aż
    0.43
     Hanks
    0.41
     аж
    0.41
    اٹ
    0.40
     அர
    0.40
    浓
    0.40
    فی
    0.39
    Activations Density 0.000%

    No Known Activations