© 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. 96842
    Prev
    Next
    INDEX
    Explanations

    lists of written information

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

    cost per call or token

    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
    ड
    0.58
    가
    0.48
    시
    0.48
    मीडिया
    0.48
    곤
    0.47
    ช
    0.47
    드
    0.47
    พ
    0.46
    सी
    0.46
     มือ
    0.45
    POSITIVE LOGITS
     লিখে
    0.52
     লেখার
    0.47
     الرا
    0.46
     উপলব্ধ
    0.46
     রাতের
    0.45
     निदान
    0.44
    砟
    0.44
    fordern
    0.44
     রাতে
    0.44
     સમયે
    0.43
    Activations Density 0.002%

    No Known Activations