© 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. 159018
    Prev
    Next
    INDEX
    Explanations

    farm equipment

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

    forests can collect rain

    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
    bottlecap
    0.54
     हथ
    0.50
    ட்டால்
    0.50
     goomba
    0.50
    cccnc
    0.49
    <unused1886>
    0.48
    starcore
    0.47
    crocodile
    0.47
    ้องกัน
    0.47
     акчага
    0.47
    POSITIVE LOGITS
     Seats
    0.55
     seats
    0.54
     Spend
    0.51
    ’
    0.51
     Appropriate
    0.51
     So
    0.50
     Journals
    0.50
     Vol
    0.49
     Infrastructure
    0.49
     Advisors
    0.49
    Activations Density 0.000%

    No Known Activations