© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 213261
    Prev
    Next
    INDEX
    Explanations

    products or services fulfillment

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

    listing brainstormed terms

    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
    Negative Logits
    CONTAIN
    0.43
     दिनों
    0.43
     रखो
    0.42
    闭
    0.42
    ఘ
    0.41
    相当于
    0.40
    ات
    0.40
    INTEGER
    0.40
    琇
    0.40
    חה
    0.40
    POSITIVE LOGITS
     conspicuously
    0.48
    laptop
    0.48
     squir
    0.47
     আ
    0.46
     straw
    0.46
     milk
    0.46
     straws
    0.46
     płyt
    0.46
    ')])
    0.45
    shield
    0.45
    Activations Density 0.000%

    No Known Activations