© 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. 211077
    Prev
    Next
    INDEX
    Explanations

    numbers, zip code, desktops

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

    hesitation fillers

    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
     perturbed
    0.46
    लिप
    0.45
    руппа
    0.45
    _
    0.45
    example
    0.44
    סי
    0.44
    ﻌ
    0.43
    茄
    0.43
    spacing
    0.43
    чи
    0.42
    POSITIVE LOGITS
    hatan
    0.47
     หล
    0.44
     théra
    0.43
     دیگری
    0.43
     สื
    0.42
    दंड
    0.41
     जाने
    0.41
     तीर्थ
    0.41
     microorganisms
    0.41
     जलाश
    0.40
    Activations Density 0.001%

    No Known Activations