© 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. 151965
    Prev
    Next
    INDEX
    Explanations

    the word text

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

    text modifiers

    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
    ’
    1.02
    ied
    0.99
    ato
    0.88
    kyt
    0.88
    arı
    0.87
    𝒕
    0.87
    ियां
    0.86
    ely
    0.84
    kiego
    0.84
    tat
    0.81
    POSITIVE LOGITS
     be
    1.10
    是由
    1.00
    ма
    0.99
    ని
    0.97
    文本
    0.96
    是因为
    0.96
    ။
    0.96
     it
    0.95
    ي
    0.92
    它
    0.92
    Activations Density 0.036%

    No Known Activations