© 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. 149340
    Prev
    Next
    INDEX
    Explanations

    followed by words like 'me', 'the', 'a'

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

    price, value, or quantity

    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
    łej
    0.46
    最初は
    0.45
     בע
    0.45
     בכ
    0.43
     በኋላ
    0.43
    瀋
    0.42
     บน
    0.42
     возь
    0.41
     লইয়া
    0.41
     되지
    0.41
    POSITIVE LOGITS
     $
    0.52
    جاز
    0.44
     எனது
    0.44
    spot
    0.43
     rectal
    0.41
    ena
    0.41
     परमात्मा
    0.41
     races
    0.41
    etary
    0.40
    orges
    0.40
    Activations Density 0.000%

    No Known Activations