© 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. 221523
    Prev
    Next
    INDEX
    Explanations

    Peter’s

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

    choker appears

    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
     مک
    0.50
    閫
    0.49
    ແ
    0.47
    遌
    0.46
     accion
    0.46
    ovll
    0.46
     książ
    0.45
    涳
    0.45
    এম
    0.45
     নদীর
    0.45
    POSITIVE LOGITS
     pest
    0.46
    volver
    0.46
     Fancy
    0.45
     traversal
    0.45
    fif
    0.45
     গিয়েছে
    0.45
    get
    0.44
    or
    0.44
    pros
    0.42
    prone
    0.42
    Activations Density 0.000%

    No Known Activations