© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2296
    Prev
    Next
    INDEX
    Explanations

    asking for what excites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    rans
    0.69
    ধানে
    0.64
    variable
    0.63
     ductile
    0.63
    ర్ప
    0.62
    ächst
    0.61
    <0xA2>
    0.60
     됩니다
    0.60
    槸
    0.60
    付き
    0.60
    POSITIVE LOGITS
     appealed
    2.20
     appeals
    2.13
     appeal
    2.10
     excites
    2.10
     excite
    1.98
     intrig
    1.89
     intrigued
    1.86
     piqu
    1.85
     Appeal
    1.83
     inspires
    1.80
    Activations Density 0.637%

    No Known Activations