© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23908
    Prev
    Next
    INDEX
    Explanations

    modeling for an editorial

    np_acts-logits-general · gemini-2.5-flash-lite

    building, programming, coding, robotics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DENUMIRE
    0.54
     үчүн
    0.52
     yǔ
    0.51
     円
    0.49
     為
    0.49
    کروچ
    0.48
     うち
    0.48
     これ
    0.47
     なお
    0.47
     மொழ
    0.46
    POSITIVE LOGITS
    n
    0.49
    </i>
    0.48
    Peaks
    0.47
    явить
    0.47
    Around
    0.46
    </h3>
    0.46
    Motor
    0.46
     was
    0.46
    Ty
    0.46
    Your
    0.44
    Activations Density 0.000%

    No Known Activations