© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2479
    Prev
    Next
    INDEX
    Explanations

    exclamations after greetings or affirmations

    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_16k_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
    ____________
    1.07
    _______
    1.06
    ________________
    1.03
    __________
    1.03
    ________
    1.02
    ___________
    1.01
    ______________
    1.00
    _______________
    0.95
     ____________
    0.95
    ____
    0.95
    POSITIVE LOGITS
    !
    4.21
    !
    3.43
    !)
    3.40
    !"
    3.39
    !!
    3.39
     !
    3.27
    !\
    3.23
    !”
    3.21
    !`
    3.18
    !</
    3.15
    Activations Density 0.782%

    No Known Activations