© 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. 142219
    Prev
    Next
    INDEX
    Explanations

    after the delivery

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

    spiritual beings and art

    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
     Leute
    0.49
     causes
    0.49
     Groups
    0.47
    豚
    0.46
     debuts
    0.46
    rones
    0.45
     guarantees
    0.45
    HB
    0.44
     Reactions
    0.44
     steals
    0.44
    POSITIVE LOGITS
    visualization
    0.54
    resourceUrl
    0.48
    provide
    0.48
     জীব
    0.47
    expec
    0.47
    可视化
    0.47
    in
    0.47
    érrez
    0.46
    눔
    0.46
    ຕ້ອງ
    0.45
    Activations Density 0.000%

    No Known Activations