© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 85600
    Prev
    Next
    INDEX
    Explanations

    states white Names bathroom bind God scent design

    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_16_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
    ět
    0.91
    il
    0.80
    ítás
    0.71
    ére
    0.68
    ért
    0.67
    崱
    0.67
    éb
    0.66
    பட்ச
    0.65
    ősz
    0.63
    ísticas
    0.61
    POSITIVE LOGITS
    ット
    0.70
    ی
    0.63
    ལ་
    0.63
     manic
    0.63
    دى
    0.61
     hanno
    0.60
     avrebbe
    0.59
     ovat
    0.59
    が多く
    0.59
     disegnare
    0.58
    Activations Density 0.000%

    No Known Activations