© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1997
    Prev
    Next
    INDEX
    Explanations

    ready to start

    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
     দিব
    0.77
    忤
    0.71
     salva
    0.68
    殇
    0.67
     disagreeable
    0.67
     logout
    0.64
     shame
    0.64
     insult
    0.64
    狲
    0.64
     violated
    0.64
    POSITIVE LOGITS
     excitement
    3.41
     excited
    3.09
     anticipation
    2.97
    excited
    2.78
     Excited
    2.75
     eagerly
    2.72
    Exc
    2.68
     excitedly
    2.63
     excite
    2.58
     excitation
    2.52
    Activations Density 0.840%

    No Known Activations