© 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. 219675
    Prev
    Next
    INDEX
    Explanations

    responsibilities and agreements

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

    important note

    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
     chamber
    0.55
     Chambers
    0.53
     chambers
    0.51
    oni
    0.49
    ,
    0.48
    anut
    0.46
     ceramics
    0.46
     Whitehead
    0.46
    …
    0.46
     cane
    0.45
    POSITIVE LOGITS
    ్ఞ
    0.51
     사용하는
    0.48
     숫자
    0.48
     자리
    0.46
     주제
    0.46
     الأمريكية
    0.46
    льными
    0.45
    טורק
    0.45
     말했다
    0.45
    ప్
    0.45
    Activations Density 0.000%

    No Known Activations