© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204713
    Prev
    Next
    INDEX
    Explanations

    data, figures, examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     palavras
    0.49
     bleiben
    0.47
     overflows
    0.47
     সর্বদা
    0.47
     тільки
    0.46
     instituições
    0.46
    𝗽
    0.46
     inoxyd
    0.45
    引き続き
    0.45
     apenas
    0.45
    POSITIVE LOGITS
    o
    0.52
    initpos
    0.52
     at
    0.48
    Credit
    0.47
    Business
    0.44
    ském
    0.44
    ur
    0.44
    icrosoft
    0.44
    ského
    0.43
    scriptstyle
    0.43
    Activations Density 0.002%

    No Known Activations