© 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. 50357
    Prev
    Next
    INDEX
    Explanations

    Apple Watch

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

    observed proportions ratios abundance

    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
    students
    0.56
    marca
    0.50
    pairs
    0.48
    Users
    0.47
    蝗
    0.47
    labels
    0.47
    oga
    0.47
    бай
    0.47
     ㄱ
    0.46
     עס
    0.46
    POSITIVE LOGITS
     dominions
    0.52
     clandestine
    0.46
     magist
    0.46
     devrez
    0.46
     relic
    0.45
     neutrality
    0.45
     neut
    0.45
     capitale
    0.45
     fondamentale
    0.44
     zast
    0.43
    Activations Density 0.000%

    No Known Activations