© 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. 152211
    Prev
    Next
    INDEX
    Explanations

    Blog invite provisions signed survival

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

    Google plan benefits

    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
     Classification
    0.50
     Workshops
    0.50
     new
    0.47
     ++
    0.47
     Dept
    0.47
    ↵
    0.46
     Summary
    0.46
     Grading
    0.46
     =
    0.46
     workshops
    0.45
    POSITIVE LOGITS
    タオル
    0.50
     religiosos
    0.49
     legitt
    0.49
    боре
    0.48
    髄
    0.48
    検討
    0.47
     agrí
    0.47
    itere
    0.47
    तेरे
    0.47
    ன
    0.47
    Activations Density 0.001%

    No Known Activations