© 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. 11306
    Prev
    Next
    INDEX
    Explanations

    of + noun/gerund

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

    generating, improving, creating, being

    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
    the
    0.68
     the
    0.63
    ل
    0.63
    р
    0.58
     aspects
    0.58
     policies
    0.57
     ils
    0.57
     bouts
    0.54
     or
    0.54
     identities
    0.54
    POSITIVE LOGITS
    '
    0.64
    being
    0.54
     появление
    0.54
     being
    0.51
     étant
    0.50
    tidak
    0.50
    áno
    0.49
    ération
    0.48
     πρώτη
    0.48
    人が
    0.48
    Activations Density 0.165%

    No Known Activations