© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 133439
    Prev
    Next
    INDEX
    Explanations

    German words

    np_acts-logits-general · gemini-2.5-flash-lite

    use a formula to determine which cells to format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     gemidd
    0.52
     žiad
    0.51
    想要的
    0.47
     xét
    0.47
     žád
    0.47
    ähän
    0.47
     強
    0.46
     correção
    0.46
    صیٰ
    0.45
     সংক্রমণের
    0.45
    POSITIVE LOGITS
     Wirtschaft
    0.41
     Doppel
    0.41
    Bayern
    0.41
     Teich
    0.40
    wirtschaft
    0.40
    TER
    0.39
    Witt
    0.39
    s
    0.39
     Witt
    0.39
     Secret
    0.38
    Activations Density 0.003%

    No Known Activations