© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 190544
    Prev
    Next
    INDEX
    Explanations

    the rate of

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

    list items or enumerations

    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
    ęła
    0.52
    윌
    0.50
    <unused100>
    0.50
     거짓
    0.49
    进行了
    0.48
     rozpoczę
    0.48
    aliśmy
    0.48
    ą
    0.48
    ജെ
    0.48
    Chhattisgarh
    0.48
    POSITIVE LOGITS
     shelf
    0.45
     commodities
    0.44
     law
    0.42
     links
    0.42
     ions
    0.42
     kh
    0.42
     "",
    0.42
     reacted
    0.42
     dissemin
    0.41
     substance
    0.41
    Activations Density 0.003%

    No Known Activations