© 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. 216854
    Prev
    Next
    INDEX
    Explanations

    Autopilot, accounts, baby, honored

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

    discussion or how-to instructions

    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
    Imagem
    0.46
    }-\
    0.45
    ాల్
    0.45
    委員会
    0.45
    getRedTeam
    0.45
     कमेटी
    0.45
    Lip
    0.44
    Committee
    0.44
    ණ්
    0.44
    ותר
    0.44
    POSITIVE LOGITS
     ඇ
    0.46
    navigate
    0.45
     navigate
    0.44
     جگہ
    0.44
    ])$.
    0.44
     spalle
    0.44
     перший
    0.43
     দৈর্ঘ্য
    0.42
    োদ্ধ
    0.42
     collar
    0.42
    Activations Density 0.000%

    No Known Activations