© 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-16K
    7. 2959
    Prev
    Next
    INDEX
    Explanations

    informal greetings

    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
    <unused346>
    0.82
     Cela
    0.72
     Sigh
    0.70
     만들기
    0.69
     Nz
    0.69
    しているので
    0.68
     unattractive
    0.68
     irrational
    0.68
    ).)
    0.68
     }^{
    0.67
    POSITIVE LOGITS
     outta
    1.90
     ya
    1.87
     yer
    1.80
     gonna
    1.80
     goin
    1.78
     ain
    1.74
     someth
    1.74
     bein
    1.65
     kinda
    1.52
     gotta
    1.52
    Activations Density 0.326%

    No Known Activations