© 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. 54542
    Prev
    Next
    INDEX
    Explanations

    not available or provided

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

    no description or reason provided

    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
     ប
    0.47
     브랜드
    0.46
     배치
    0.46
     점
    0.45
     있습니다
    0.44
     ધો
    0.43
     수는
    0.43
     지원
    0.43
    開放
    0.43
    筮
    0.43
    POSITIVE LOGITS
    owało
    0.61
    owały
    0.44
    ilized
    0.42
    FromBody
    0.40
    描写
    0.40
    ूम
    0.38
    ้อง
    0.38
    ompany
    0.38
    ूर्ण
    0.38
     afterward
    0.38
    Activations Density 0.001%

    No Known Activations