© 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. 1886
    Prev
    Next
    INDEX
    Explanations

    lists with punctuation

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

    only

    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
     adventures
    0.29
    战争
    0.27
     burgeoning
    0.26
     sensibilities
    0.26
     extol
    0.26
     inescap
    0.25
     reimag
    0.25
    诓
    0.25
     мира
    0.25
    טים
    0.25
    POSITIVE LOGITS
     \
    0.28
     $
    0.26
     NULL
    0.26
     \%
    0.26
     فقط
    0.25
     小
    0.25
     =-\
    0.25
     Substituting
    0.24
     only
    0.24
     $\
    0.24
    Activations Density 0.000%

    No Known Activations