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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 7751
    Prev
    Next
    INDEX
    Explanations

    .jpg

    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_40_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
     miesią
    0.40
    )
    0.39
     Sumatra
    0.38
     Worcestershire
    0.37
     Ryanair
    0.37
     samoch
    0.36
     Country
    0.35
     Mayweather
    0.35
     Antibodies
    0.34
    .')
    0.34
    POSITIVE LOGITS
    挕
    0.45
    <unused2020>
    0.44
     maneu
    0.42
    <unused1917>
    0.40
    が存在
    0.40
    <unused625>
    0.40
     इंस्टीट्यूट
    0.39
     निकालेंगे
    0.39
    <unused635>
    0.39
     पेंगे
    0.38
    Activations Density 0.000%

    No Known Activations