© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8505
    Prev
    Next
    INDEX
    Explanations

    short

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

    short

    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
    हाबाद
    0.35
    igsaw
    0.35
    Ꮭ
    0.34
    耆
    0.32
    anyol
    0.32
     ентитету
    0.32
     mãi
    0.31
    ួក
    0.31
    नाज
    0.31
    othelial
    0.31
    POSITIVE LOGITS
     short
    5.13
    short
    4.91
    短
    4.78
     Short
    4.72
    Short
    4.72
     SHORT
    4.72
     корот
    4.63
    SHORT
    4.41
     kısa
    4.28
     짧
    4.25
    Activations Density 0.496%

    No Known Activations