© 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. 101435
    Prev
    Next
    INDEX
    Explanations

    proper nouns

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

    multi-pillar system, outlook, arrested, scouting, knives, relative, easy

    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
    د
    0.70
    дт
    0.54
    depend
    0.50
    دست
    0.50
    র
    0.49
    어서
    0.49
    ل
    0.48
    се
    0.48
    dispers
    0.47
    Liquid
    0.46
    POSITIVE LOGITS
     Ched
    0.61
     Kaitlyn
    0.58
     croissant
    0.55
     ép
    0.54
     Ner
    0.52
     Nara
    0.52
     Abdul
    0.51
     Croft
    0.51
     Sheffield
    0.50
     Kham
    0.50
    Activations Density 0.000%

    No Known Activations