© 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. 70055
    Prev
    Next
    INDEX
    Explanations

    numbers and specific items

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

    introductory phrases and concepts

    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
    agée
    0.54
    ClientID
    0.49
    ardier
    0.48
     ದಾಖ
    0.48
    expiry
    0.47
    Expire
    0.47
    䄱
    0.47
    delay
    0.45
    Reporting
    0.45
    获奖
    0.45
    POSITIVE LOGITS
     piped
    0.48
    .*
    0.45
    ↵
    0.45
     콜
    0.44
     구
    0.44
     죽
    0.44
    싶
    0.44
     tear
    0.44
    सिल
    0.44
    вам
    0.44
    Activations Density 0.000%

    No Known Activations