© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18710
    Prev
    Next
    INDEX
    Explanations

    punctuation and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ریل
    0.41
     நேரடியாக
    0.41
    *}$
    0.38
     agad
    0.38
    thenReturn
    0.37
    それぞれの
    0.37
    當然
    0.36
    もら
    0.35
    ᵢ
    0.35
    আর
    0.35
    POSITIVE LOGITS
     _,
    0.47
    -,
    0.46
     $,
    0.45
     ?,
    0.43
     peregr
    0.43
    %,
    0.42
    ,
    0.42
    (),
    0.42
     ،
    0.41
    (',',
    0.41
    Activations Density 0.005%

    No Known Activations