© 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. 222278
    Prev
    Next
    INDEX
    Explanations

    along the

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

    describing shapes and proportions

    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
    o
    0.49
     přes
    0.48
    mj
    0.47
    सनी
    0.47
     muu
    0.45
    ự
    0.44
     cultivate
    0.44
     ढांचे
    0.44
     modernas
    0.43
    mz
    0.43
    POSITIVE LOGITS
    あら
    0.50
     introns
    0.47
    。
    0.46
     dehydrogenase
    0.45
     alan
    0.45
    🟡
    0.44
     a
    0.44
    intent
    0.44
    '
    0.43
    一個
    0.42
    Activations Density 0.000%

    No Known Activations