© 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. 20928
    Prev
    Next
    INDEX
    Explanations

    states of change

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

    growth and yields

    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
    convén
    0.50
     долла
    0.44
     সৎ
    0.44
     покупки
    0.43
    ɽ
    0.42
     покупать
    0.42
    acquisto
    0.41
    有不少
    0.40
    чный
    0.40
     четы
    0.39
    POSITIVE LOGITS
     suppressed
    0.46
     fantasy
    0.43
     levels
    0.43
     aberr
    0.43
     porn
    0.42
     variants
    0.41
     systems
    0.41
     görünt
    0.41
    -}\
    0.41
    بری
    0.40
    Activations Density 0.000%

    No Known Activations