© 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. 6312
    Prev
    Next
    INDEX
    Explanations

    years ending in 6 or names

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

    .TOTAL

    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
     سرمایہ
    0.26
    驄
    0.25
     බොහෝ
    0.24
     çoğu
    0.24
    lubridate
    0.24
    颀
    0.24
    धिकारियों
    0.23
     financieros
    0.23
    bindingFields
    0.23
     മണ്ണി
    0.23
    POSITIVE LOGITS
    .
    0.42
    ing
    0.36
    ة
    0.34
    )
    0.34
    :
    0.33
    ↵
    0.31
    ,
    0.31
    '
    0.31
    7
    0.31
    ING
    0.30
    Activations Density 0.953%

    No Known Activations