© 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. 146355
    Prev
    Next
    INDEX
    Explanations

    other items or references

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

    float attached

    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
    ಝ
    0.51
    oksatta
    0.47
    stylesheets
    0.45
     discharg
    0.44
    clearfix
    0.43
    nous
    0.43
     exoner
    0.43
     დ
    0.42
    noscript
    0.42
     defray
    0.42
    POSITIVE LOGITS
     CELLS
    0.48
    ിക്കും
    0.45
    ാമ
    0.44
     чём
    0.43
    Cells
    0.43
    ോക
    0.42
     আয়নগুলির
    0.42
    Its
    0.41
    界的
    0.41
    REC
    0.40
    Activations Density 0.000%

    No Known Activations