© 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. 96463
    Prev
    Next
    INDEX
    Explanations

    some form of

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

    explaining why and listing some

    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
    to
    0.58
    0.50
    er
    0.48
    bra
    0.47
     AI
    0.47
    p
    0.46
     foglie
    0.46
    格子
    0.44
     DJ
    0.44
     Hef
    0.44
    POSITIVE LOGITS
     zupeł
    0.61
     생
    0.55
     ইরা
    0.52
     אר
    0.52
     书
    0.52
     주요
    0.52
    활동
    0.52
     নিয়ন্ত্রণ
    0.51
     전략
    0.50
     देम
    0.50
    Activations Density 0.000%

    No Known Activations