© 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. 112084
    Prev
    Next
    INDEX
    Explanations

    toxic effects, detective work, fixture files, regular use

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

    file representation

    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
    dır
    0.53
     missp
    0.47
    weisung
    0.46
    listening
    0.42
    did
    0.41
    drive
    0.40
    daki
    0.40
    丰
    0.40
     confirmer
    0.40
    会議
    0.39
    POSITIVE LOGITS
     하겠습니다
    0.49
     платфор
    0.47
     patrones
    0.46
     exámenes
    0.46
    тки
    0.46
    昍
    0.46
     electrónica
    0.45
    BST
    0.45
     общества
    0.45
    )-\
    0.45
    Activations Density 0.000%

    No Known Activations