© 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. 168288
    Prev
    Next
    INDEX
    Explanations

    God, many, fingers, ways, part, you, Group

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

    explaining each clause

    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
     chegar
    0.61
     iguais
    0.56
     uma
    0.55
     attaque
    0.54
     gemaakt
    0.52
    ě
    0.52
     acredit
    0.51
     zim
    0.51
     muziek
    0.51
     perfeito
    0.50
    POSITIVE LOGITS
    理论
    0.45
    crypt
    0.42
    舴
    0.41
    Linea
    0.40
    sebastian
    0.40
    Constructor
    0.40
     સમ
    0.40
    弁
    0.40
     ಅಧ್ಯ
    0.39
    angk
    0.39
    Activations Density 0.000%

    No Known Activations