© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100876
    Prev
    Next
    INDEX
    Explanations

    academic equivalents

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

    preventive care

    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
     Z
    0.57
     E
    0.56
     Е
    0.50
     S
    0.50
     queryset
    0.49
     Viagra
    0.47
     F
    0.47
     vot
    0.45
     З
    0.45
     dòng
    0.45
    POSITIVE LOGITS
    শিরোনাম
    0.48
    transformer
    0.47
    農業
    0.45
    Manipulation
    0.45
    manha
    0.44
    parsing
    0.44
    แหล่ง
    0.44
    siblings
    0.44
    な
    0.44
    itamins
    0.43
    Activations Density 0.000%

    No Known Activations