© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1222
    Prev
    Next
    INDEX
    Explanations

    mention history

    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_9_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
    czne
    1.32
    প্ট
    1.31
    ,$$
    1.30
    MAE
    1.25
    ക്കുറിച്ച്
    1.23
    oreau
    1.20
    cms
    1.18
    मिस्ट्री
    1.18
    axies
    1.17
     Westfield
    1.15
    POSITIVE LOGITS
    ва
    1.44
    тем
    1.11
     rémun
    1.10
    я
    1.08
    ваны
    1.05
    콤
    1.04
    ौला
    1.04
    é
    1.01
     feedwater
    1.00
    тяну
    1.00
    Activations Density 0.000%

    No Known Activations