© 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. 7502
    Prev
    Next
    INDEX
    Explanations

    = character usage

    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
     a
    0.36
     〢
    0.33
     Crohn
    0.30
    —.
    0.30
     an
    0.29
    Jähr
    0.28
    élevage
    0.28
    StillWater
    0.28
     Vereinigten
    0.27
    ;&#
    0.27
    POSITIVE LOGITS
    на
    0.51
    i
    0.50
    ون
    0.48
    ста
    0.47
    માં
    0.47
    ни
    0.46
    ர்
    0.44
    ي
    0.43
    다
    0.43
    z
    0.42
    Activations Density 0.167%

    No Known Activations