© 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. 99262
    Prev
    Next
    INDEX
    Explanations

    returned to

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

    manage what

    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
    ihydro
    0.48
    nX
    0.46
    ന്ത്യ
    0.46
    anov
    0.46
    ()}>
    0.46
    terus
    0.45
     ক্রমাগত
    0.44
     ہندوستان
    0.44
    '>{
    0.43
     прода
    0.42
    POSITIVE LOGITS
     Edith
    0.54
     symbol
    0.53
     derog
    0.48
     visually
    0.48
     lil
    0.48
     Chelsea
    0.47
     bl
    0.46
     Dominique
    0.46
     Bl
    0.46
     diễn
    0.46
    Activations Density 0.000%

    No Known Activations