© 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. 86326
    Prev
    Next
    INDEX
    Explanations

    achieved, debt, system, courses, data, sites

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

    word pairs or programming 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
    變
    0.52
    ག
    0.48
    飾り
    0.48
    に
    0.46
    문의
    0.46
    རྒྱ
    0.46
     život
    0.46
    ORIG
    0.46
    細かい
    0.46
    贖
    0.46
    POSITIVE LOGITS
     Johnson
    0.52
     Bere
    0.43
     johnson
    0.43
     Minister
    0.43
     Архивировано
    0.42
    Johnson
    0.42
    </sup>
    0.42
    Bere
    0.42
     anticipated
    0.40
     pastors
    0.40
    Activations Density 0.001%

    No Known Activations