© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1
    Prev
    Next
    INDEX
    Explanations

    Finnish and Estonian text fragments

    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
     already
    1.04
     masquer
    1.03
     reliant
    1.02
     frequented
    1.01
    і
    1.00
    Regards
    0.97
     बन
    0.97
     concomitant
    0.97
    І
    0.97
     cans
    0.97
    POSITIVE LOGITS
     tä
    1.36
     työ
    1.35
     sekä
    1.33
     erity
    1.30
     mitä
    1.26
     tämän
    1.24
     maail
    1.23
     myös
    1.23
     vaiht
    1.23
     kesk
    1.23
    Activations Density 0.033%

    No Known Activations