© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2346
    Prev
    Next
    INDEX
    Explanations

    filling blanks or correcting sentences

    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_22_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
    🛡
    0.74
     Neue
    0.66
     Nov
    0.65
     Skip
    0.65
     Oct
    0.64
     Rek
    0.64
     Artisan
    0.60
     Define
    0.60
    ⚡
    0.59
     Create
    0.59
    POSITIVE LOGITS
     adverb
    1.23
     আমার
    1.19
     oración
    1.17
     raining
    1.15
     ___
    1.14
    ?/
    1.13
     /(
    1.13
     ／
    1.13
    incerely
    1.12
     /$
    1.12
    Activations Density 1.315%

    No Known Activations