© 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. 182161
    Prev
    Next
    INDEX
    Explanations

    common phrases and compound words

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

    preceded by specific phrases

    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
    ień
    0.54
    ہ
    0.53
    ífica
    0.51
     ﺍﻟ
    0.50
    uia
    0.50
    츠
    0.49
    u
    0.48
    ünüz
    0.47
    ﺂ
    0.47
    üman
    0.47
    POSITIVE LOGITS
    dpi
    0.51
     bout
    0.44
     Transmission
    0.43
     DPI
    0.43
     plumber
    0.42
     metabolized
    0.42
     Bazaar
    0.42
     be
    0.41
     selepas
    0.41
     masker
    0.41
    Activations Density 0.000%

    No Known Activations