© 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. 112951
    Prev
    Next
    INDEX
    Explanations

    goblin | CTC | new additions

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

    undertone, saveDOMToFile, transaction lists, PCB layout, sending business

    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
     amic
    0.48
    icker
    0.47
     &
    0.47
    ise
    0.47
    inib
    0.45
    icle
    0.43
    inct
    0.43
    5
    0.43
    cription
    0.43
    4
    0.43
    POSITIVE LOGITS
    钻
    0.49
    ิติ
    0.47
     চূ
    0.45
    oblins
    0.45
    向前
    0.44
     jButton
    0.42
    Canc
    0.42
     goblin
    0.42
     निरा
    0.42
    ったら
    0.42
    Activations Density 0.001%

    No Known Activations