© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8850
    Prev
    Next
    INDEX
    Explanations

    Finnish 'pa' prefix for verb past tense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
     حساس
    1.30
    ąg
    1.11
    ế
    1.04
    essoal
    1.01
    өт
    1.00
    äll
    0.99
    abbo
    0.99
    ंकन
    0.97
    hemm
    0.97
    ą
    0.97
    POSITIVE LOGITS
    dfunding
    1.39
    ourcing
    1.28
    FOOT
    1.15
    thorne
    1.10
    foot
    1.05
    ther
    1.04
    neas
    1.01
    feet
    0.99
     feet
    0.99
    дить
    0.97
    Activations Density 0.007%

    No Known Activations