© 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. 109165
    Prev
    Next
    INDEX
    Explanations

    Tasting Collection

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

    ever flown, stop sampling, greatest of

    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
     impending
    0.43
     criss
    0.42
     PEACE
    0.42
    ความ
    0.42
    \
    0.40
     மூன்று
    0.40
     looming
    0.40
     motor
    0.40
    時計
    0.39
     sociétés
    0.39
    POSITIVE LOGITS
    WithOptions
    0.52
    тивна
    0.49
    שו
    0.49
    тивний
    0.49
     Фургала
    0.48
    butoxy
    0.47
     विकल्प
    0.47
    冪
    0.47
    Virtualized
    0.46
    𒅆
    0.46
    Activations Density 0.001%

    No Known Activations