© 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. 201692
    Prev
    Next
    INDEX
    Explanations

    fractional part or contractual

    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
    Innovation
    0.49
    Disk
    0.45
    Funding
    0.42
    Algorithm
    0.42
    心を
    0.42
    ゝ
    0.42
    Feb
    0.41
     सीखेंगे
    0.41
    Plus
    0.41
    Fcn
    0.40
    POSITIVE LOGITS
     sofern
    0.47
     Emit
    0.46
     VARCHAR
    0.45
    ');
    0.44
     with
    0.43
     Savannah
    0.43
     smoking
    0.43
    text
    0.42
     Trace
    0.42
    ';
    0.42
    Activations Density 0.001%

    No Known Activations