© 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. 177881
    Prev
    Next
    INDEX
    Explanations

    local physician

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

    comments and code structures

    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
    ウ
    0.46
    惹
    0.46
    危害
    0.46
    撕
    0.46
    十年
    0.44
     culoare
    0.44
    у
    0.44
    ாத
    0.44
     தச
    0.44
    み
    0.44
    POSITIVE LOGITS
     GATT
    0.54
     wondered
    0.52
     amongst
    0.50
     assistants
    0.50
     hardwoods
    0.50
     breeds
    0.49
    érieurs
    0.49
     Agents
    0.48
     noted
    0.48
     agents
    0.48
    Activations Density 0.000%

    No Known Activations