© 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. 133440
    Prev
    Next
    INDEX
    Explanations

    projects, loved, materials

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

    words typically followed by punctuation

    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
    也就
    0.42
     исключительно
    0.41
     हित
    0.40
    辭
    0.40
     बीते
    0.38
     inadequacy
    0.38
    ក្រ
    0.38
    whitespace
    0.38
    Ħ
    0.37
     undeniably
    0.37
    POSITIVE LOGITS
     Collectors
    0.52
     Chirurg
    0.46
    ্তির
    0.46
     Ս
    0.46
     welkom
    0.46
     Everywhere
    0.46
     Бі
    0.45
     Commanders
    0.45
     normalement
    0.45
     Donec
    0.44
    Activations Density 0.001%

    No Known Activations