© 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. 106861
    Prev
    Next
    INDEX
    Explanations

    withdrawal from", "He was", "two other", "Fortunato", "rider"

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

    gratitude, fireball, sacrifice

    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
    Ia
    0.47
     fara
    0.47
    í
    0.44
    é
    0.44
     zostanie
    0.43
     hely
    0.42
    タリー
    0.42
    spotify
    0.41
     Kontrolle
    0.41
    ulint
    0.41
    POSITIVE LOGITS
    ۟
    0.44
     বরাবর
    0.43
     주고
    0.42
     ಯಾವಾಗ
    0.42
    재
    0.42
     Legs
    0.41
    UTCTime
    0.41
     takers
    0.40
    Під
    0.40
     USE
    0.40
    Activations Density 0.001%

    No Known Activations