© 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. 101326
    Prev
    Next
    INDEX
    Explanations

    ordinal rankings and counts

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

    choosing specific role

    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
     Commencez
    0.46
     சம்ப
    0.46
    ക്കാം
    0.45
     श्रेणी
    0.45
     मॉक
    0.45
    鐏
    0.44
    leyebilirsiniz
    0.44
    ravy
    0.44
     সাইফুদ্দিন
    0.44
    閩
    0.44
    POSITIVE LOGITS
     Cooperation
    0.46
     cooperation
    0.46
     atraves
    0.44
     ´
    0.43
     Moscow
    0.41
     beragam
    0.41
     happ
    0.40
     menilai
    0.40
     Happ
    0.40
    กระท
    0.40
    Activations Density 0.001%

    No Known Activations