© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137052
    Prev
    Next
    INDEX
    Explanations

    mathematical and technical definitions

    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
    ח
    0.48
    枞
    0.47
     Correlation
    0.46
     Conservation
    0.46
     suggestive
    0.46
     correlated
    0.44
    充满
    0.43
     consolation
    0.43
    朦
    0.43
     correlations
    0.43
    POSITIVE LOGITS
    otimes
    0.46
    owią
    0.46
    urls
    0.46
    érence
    0.46
     Marcin
    0.45
    venes
    0.44
    léans
    0.43
    su
    0.43
    cu
    0.43
    quillo
    0.43
    Activations Density 0.004%

    No Known Activations