© 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-16K
    7. 7271
    Prev
    Next
    INDEX
    Explanations

    macro, define, alias, newcommand

    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_16k_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
    ண்கள்
    0.46
    ären
    0.44
     convexo
    0.44
    ರ್ಮ
    0.43
     Leningrad
    0.43
    खेल
    0.42
    OU
    0.41
    <h1>
    0.41
    mation
    0.41
     Topology
    0.41
    POSITIVE LOGITS
     به
    0.49
    an
    0.48
    ث
    0.47
     похід
    0.46
    t
    0.45
    ت
    0.45
    غ
    0.44
    া
    0.44
    ed
    0.44
    ل
    0.43
    Activations Density 0.016%

    No Known Activations