© 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. 158911
    Prev
    Next
    INDEX
    Explanations

    academic citations and specific locations

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

    certain formal or technical contexts

    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
     behem
    0.46
    inputs
    0.46
    ugg
    0.44
    ни
    0.43
    ся
    0.42
    Inputs
    0.42
    о
    0.42
     ১৯৮
    0.41
    -
    0.41
    у
    0.41
    POSITIVE LOGITS
     Epistle
    0.49
     बैक्टी
    0.47
     etiam
    0.47
     BIRTH
    0.47
     DEPARTMENT
    0.46
     Wrist
    0.45
     idx
    0.44
     preface
    0.44
    erà
    0.43
     beper
    0.43
    Activations Density 0.000%

    No Known Activations