© 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. 200547
    Prev
    Next
    INDEX
    Explanations

    section number or figure reference

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

    why and need

    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
    贾
    0.50
    姒
    0.49
    🐆
    0.47
    ittu
    0.47
    Arkadaşlar
    0.46
    甲烷
    0.46
     NICKEL
    0.45
    ä
    0.45
     Sahara
    0.44
    𝑵
    0.43
    POSITIVE LOGITS
     erect
    0.47
     recollect
    0.47
     reflect
    0.47
     upscale
    0.47
     双
    0.46
     ngưỡng
    0.46
     stow
    0.46
     offered
    0.45
     extend
    0.45
     επιχει
    0.45
    Activations Density 0.000%

    No Known Activations