© 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. 146504
    Prev
    Next
    INDEX
    Explanations

    pre, boston, mini, monkey, indemn, Listed, Leave

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

    body composition

    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
     acolo
    0.48
    it
    0.47
     आपल्याला
    0.41
    s
    0.41
    driving
    0.40
     마치
    0.40
    phoneNumber
    0.40
    中は
    0.40
    #
    0.40
     вода
    0.39
    POSITIVE LOGITS
    ኖች
    0.53
    뜻
    0.52
    ينات
    0.50
     Bytes
    0.48
     সহজেই
    0.47
    лік
    0.46
     Commence
    0.46
    ätzung
    0.46
    岖
    0.45
    呤
    0.45
    Activations Density 0.001%

    No Known Activations