© 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. 79095
    Prev
    Next
    INDEX
    Explanations

    hand showing, see across, fish, compressed?

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

    qualifying descriptors or categories

    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
    ，
    0.44
     "@
    0.41
     sorely
    0.41
     ～
    0.40
    #'
    0.40
    ('@
    0.39
    １
    0.39
     teammate
    0.39
     OCA
    0.39
     '@
    0.38
    POSITIVE LOGITS
     ను
    0.51
     suivant
    0.46
    dyž
    0.46
     végétation
    0.46
    lepší
    0.45
    طق
    0.45
     communément
    0.45
    ناس
    0.44
     použit
    0.44
    儡
    0.44
    Activations Density 0.001%

    No Known Activations