© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1227
    Prev
    Next
    INDEX
    Explanations

    Polish verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ینګ
    1.93
     ی
    1.68
     国
    1.61
     vague
    1.51
    国
    1.51
    وزی
    1.49
    عنی
    1.49
    ﯾ
    1.49
     solitude
    1.47
    فیر
    1.47
    POSITIVE LOGITS
     więks
    2.40
     już
    2.20
     peł
    2.20
     dług
    2.19
     tylko
    2.18
     bardzo
    2.17
     równ
    2.17
     jeszcze
    2.16
     między
    2.13
     podstaw
    2.13
    Activations Density 0.027%

    No Known Activations