© 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. 40-GEMMASCOPE-2-RES-262K
    7. 29131
    Prev
    Next
    INDEX
    Explanations

    knows what

    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_40_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
     "="
    0.55
     rebuttal
    0.51
     seguintes
    0.46
     '='
    0.46
     frac
    0.45
     FutureWarning
    0.44
     tiden
    0.43
    年份
    0.43
     finales
    0.43
     approx
    0.42
    POSITIVE LOGITS
    Anglo
    0.46
    ïd
    0.42
     synergies
    0.39
    makt
    0.39
    rà
    0.39
    锢
    0.39
     україн
    0.38
    Rosa
    0.38
    örungen
    0.37
    पट
    0.37
    Activations Density 0.000%

    No Known Activations