© 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. 67497
    Prev
    Next
    INDEX
    Explanations

    answer Garden

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

    agricultural systems and technology

    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
     לא
    0.36
    𝘫
    0.34
    )}}{\
    0.33
    יי
    0.32
    ਬ
    0.32
    מי
    0.32
    ני
    0.31
    בי
    0.31
    ਏ
    0.30
    ༡
    0.30
    POSITIVE LOGITS
    0.28
     hamburgers
    0.25
     Camera
    0.24
     fuselage
    0.24
     seconds
    0.24
     Highway
    0.23
     Trường
    0.23
     Sports
    0.23
     Burgers
    0.23
     Field
    0.23
    Activations Density 0.076%

    No Known Activations