© 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. 186565
    Prev
    Next
    INDEX
    Explanations

    spring season, jurisdiction, particles, place

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

    contrasting ideas using 'than'

    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
    дку
    0.52
     строку
    0.52
    퇸
    0.49
    Coref
    0.49
    কে
    0.48
    стров
    0.46
    llen
    0.46
    ίνη
    0.46
    Picker
    0.45
    товано
    0.45
    POSITIVE LOGITS
     hyper
    0.46
     ブラック
    0.46
     hiper
    0.46
     ブランド
    0.46
     ಸ
    0.45
     publicité
    0.45
     broadest
    0.45
     distintos
    0.44
     Hé
    0.44
     Má
    0.44
    Activations Density 0.001%

    No Known Activations