© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5983
    Prev
    Next
    INDEX
    Explanations

    Vi followed by specific endings

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

    vibe check

    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_53_width_65k_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
    пени
    0.41
    Posting
    0.41
    ಪ್ರ
    0.41
    鐟
    0.41
    ён
    0.39
    వై
    0.38
    涑
    0.38
    鉉
    0.38
    成果
    0.37
    తులు
    0.37
    POSITIVE LOGITS
    aduct
    0.56
    ртуа
    0.55
    oodoo
    0.51
    ctor
    0.50
    ژگی
    0.49
    apour
    0.48
    hement
    0.48
    ệt
    0.47
    кторов
    0.46
    reux
    0.46
    Activations Density 0.051%

    No Known Activations