© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13626
    Prev
    Next
    INDEX
    Explanations

    action or act followed by preposition/role

    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_17_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
     punctured
    2.59
     encompasses
    2.58
     encompass
    2.57
     waving
    2.52
    Incidentally
    2.52
    כ
    2.50
    𝑨
    2.48
    kjav
    2.43
    𝒓
    2.37
     EXEMPLARY
    2.37
    POSITIVE LOGITS
    er
    3.25
    ようになりました
    2.99
    a
    2.76
    aal
    2.70
     bhi
    2.61
    éristique
    2.59
    ようになって
    2.59
    ğer
    2.58
     partielle
    2.46
     gameState
    2.44
    Activations Density 0.172%

    No Known Activations