© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128576
    Prev
    Next
    INDEX
    Explanations

    rapid action or urgency

    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
    一
    0.55
    त
    0.50
    ：
    0.48
    NESS
    0.46
    ה
    0.45
    У
    0.45
    вен
    0.44
     INTER
    0.43
    setLocation
    0.43
    Ин
    0.43
    POSITIVE LOGITS
     dangerously
    0.49
    انه
    0.49
     frantically
    0.47
     imme
    0.47
     desperately
    0.45
    യില്‍
    0.45
     stimulant
    0.44
     frantic
    0.44
    こんばんは
    0.44
    k
    0.44
    Activations Density 0.001%

    No Known Activations