© 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. 89619
    Prev
    Next
    INDEX
    Explanations

    describing, should wait, teams, Cat, climate

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

    instructions, requirements, and descriptions

    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
    员
    0.54
    闪
    0.46
    อส
    0.43
    玟
    0.43
    만을
    0.42
    证券
    0.41
    用户
    0.40
    HL
    0.40
    公演
    0.40
    用户的
    0.39
    POSITIVE LOGITS
     使っ
    0.57
    zoek
    0.48
     لحد
    0.48
     វា
    0.48
    possible
    0.47
    ləşdir
    0.47
     できる
    0.47
     loadImage
    0.46
    endedores
    0.46
    noz
    0.46
    Activations Density 0.001%

    No Known Activations