© 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. 22787
    Prev
    Next
    INDEX
    Explanations

    special characters, abbreviations and 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
    িত
    0.44
     Cosmology
    0.40
    或
    0.39
    傗
    0.39
    나
    0.38
    ره
    0.38
     provoquer
    0.37
     amplifier
    0.37
    하거나
    0.37
    وصل
    0.36
    POSITIVE LOGITS
    Trim
    0.43
    varlak
    0.42
     şu
    0.40
     bf
    0.40
    𐰣
    0.40
     danno
    0.40
     kuts
    0.40
    iletto
    0.40
     lyrics
    0.39
    °;
    0.39
    Activations Density 0.000%

    No Known Activations