© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 172
    Prev
    Next
    INDEX
    Explanations

    Polish words like Wie, Pow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    bullet
    1.26
    ที่สุด
    1.22
     Venkates
    1.20
    isiin
    1.19
    終
    1.19
    scription
    1.19
     regressions
    1.19
    หนัก
    1.18
    ッキング
    1.17
     nghiệm
    1.16
    POSITIVE LOGITS
    ła
    0.95
    że
    0.91
    ł
    0.90
    ży
    0.89
    ucie
    0.89
    ż
    0.89
    Przy
    0.88
    łe
    0.86
     się
    0.85
    Ł
    0.84
    Activations Density 0.445%

    No Known Activations