© 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. 10335
    Prev
    Next
    INDEX
    Explanations

    Subject:

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

    Subject line identifier

    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
     पड़ेगा
    0.50
     pakai
    0.45
     Daniel
    0.44
    গ্রেস
    0.43
    ometimes
    0.43
    患
    0.43
    ティア
    0.41
     restraining
    0.40
     Radcliffe
    0.40
    じ
    0.40
    POSITIVE LOGITS
     موضوع
    0.47
     खुशखबरी
    0.46
    ме
    0.45
     assunto
    0.45
    장의
    0.45
     చిత్రం
    0.45
     중요
    0.44
     asuntos
    0.43
     이미지
    0.43
     잘못
    0.43
    Activations Density 0.000%

    No Known Activations