© 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. 24599
    Prev
    Next
    INDEX
    Explanations

    result of

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

    formatting and structure

    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
    l
    0.59
     I
    0.52
    at
    0.51
    ce
    0.50
     CE
    0.48
    CE
    0.47
    I
    0.46
    eb
    0.46
    ni
    0.45
     Corporation
    0.45
    POSITIVE LOGITS
    지는
    0.55
    더라
    0.54
     sitzen
    0.54
    ўся
    0.54
     imprensa
    0.53
    지도
    0.51
    지고
    0.51
     ciddi
    0.50
     различи
    0.50
    тился
    0.49
    Activations Density 0.000%

    No Known Activations