© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126400
    Prev
    Next
    INDEX
    Explanations

    play leads to playfully

    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
     liquidated
    0.45
     Certificates
    0.45
     liqu
    0.44
    ši
    0.44
     consistent
    0.44
     condemning
    0.43
    ट
    0.43
     classifying
    0.43
     liquid
    0.42
     substring
    0.42
    POSITIVE LOGITS
    לה
    0.49
     kiến
    0.46
    lage
    0.46
     އަ
    0.46
    력
    0.46
     Huế
    0.45
    仅仅
    0.45
    ﺌ
    0.45
     ה
    0.44
    тости
    0.44
    Activations Density 0.000%

    No Known Activations