© 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. 160500
    Prev
    Next
    INDEX
    Explanations

    advice from hairstylist

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

    names and technical terms

    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
     (=
    0.51
     diameters
    0.45
     indicato
    0.44
     ولی
    0.44
     টাক
    0.42
     chops
    0.42
     κι
    0.41
     nghĩa
    0.41
     transformers
    0.40
     областях
    0.40
    POSITIVE LOGITS
     Mehmet
    0.48
     Demir
    0.43
     Erick
    0.42
    ഷ്ട്ര
    0.41
    訌
    0.41
     Rafael
    0.41
    굼
    0.41
     vehemently
    0.40
     STATE
    0.40
     OBSERV
    0.40
    Activations Density 0.001%

    No Known Activations