© 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. 31-GEMMASCOPE-2-RES-65K
    7. 7379
    Prev
    Next
    INDEX
    Explanations

    similes and examples

    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_65k_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
    ad
    0.88
    il
    0.79
    ay
    0.79
    uk
    0.79
    மாக
    0.79
    <0x80>
    0.78
     are
    0.75
    s
    0.73
    යින්
    0.70
    л
    0.69
    POSITIVE LOGITS
    '
    0.80
     داشت
    0.73
    :
    0.70
    มัน
    0.68
    1
    0.68
    Like
    0.65
    در
    0.64
    은
    0.63
     this
    0.62
     थे
    0.61
    Activations Density 0.133%

    No Known Activations