© 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. 156611
    Prev
    Next
    INDEX
    Explanations

    Scrum.org, color, surfaces, use

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

    department focus is

    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
     จับ
    0.57
    dalam
    0.51
    со
    0.50
    тами
    0.50
    Thread
    0.50
    с
    0.49
    andel
    0.48
    誢
    0.48
    andu
    0.47
     ਚ
    0.46
    POSITIVE LOGITS
     halides
    0.52
     alkyl
    0.48
     bushings
    0.46
     няма
    0.46
     externalities
    0.46
     lymphomas
    0.46
    蝗
    0.45
    鏤
    0.45
    ᱕
    0.45
     leukocytes
    0.44
    Activations Density 0.000%

    No Known Activations