© 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. 184657
    Prev
    Next
    INDEX
    Explanations

    parts of a whole

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

    automating parts, reduced near

    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
    on
    0.52
    出
    0.47
    field
    0.46
     springtime
    0.46
    並
    0.45
    満
    0.45
    spring
    0.45
    泄
    0.45
    suggest
    0.44
     seemingly
    0.44
    POSITIVE LOGITS
     它
    0.53
     היא
    0.52
     ինչ
    0.51
    ionar
    0.50
     trayectoria
    0.49
     ຫຼື
    0.49
    izantes
    0.49
    ທີ່ມີ
    0.49
     ແມ່ນ
    0.49
     கிடைத்தது
    0.48
    Activations Density 0.000%

    No Known Activations