© 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. 74757
    Prev
    Next
    INDEX
    Explanations

    talk anyway, ultimate quiz, affect attention

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

    reservations essential

    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
     rebell
    0.52
     caoutch
    0.51
    硙
    0.49
    क्रेट
    0.48
     Balliye
    0.47
     सिंहासन
    0.47
    oof
    0.47
    jenkins
    0.47
     travaillons
    0.46
    джи
    0.46
    POSITIVE LOGITS
     unsuitable
    0.48
     non
    0.48
     Mn
    0.46
    糧
    0.45
    ła
    0.45
     flowering
    0.45
    MnO
    0.45
    :
    0.44
     Blüten
    0.44
    0.44
    Activations Density 0.001%

    No Known Activations