© 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. 155870
    Prev
    Next
    INDEX
    Explanations

    phrase or idiom followed by clause

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

    estimating percentages and market share

    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
    ಠ
    0.51
    Keychain
    0.50
    Lycodon
    0.48
    穸
    0.48
    볍
    0.45
    仩
    0.45
     טוב
    0.41
    鐧
    0.41
    сього
    0.41
    silyl
    0.41
    POSITIVE LOGITS
     Lib
    0.50
     ASEAN
    0.50
     Contemporary
    0.47
     West
    0.47
     Est
    0.46
     MS
    0.46
     Ang
    0.45
     during
    0.45
     NA
    0.45
     et
    0.44
    Activations Density 0.001%

    No Known Activations