© 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. 101169
    Prev
    Next
    INDEX
    Explanations

    warranty information, repair, and more

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

    Food Court, seeking convenience

    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
    ciples
    0.54
    son
    0.53
    lda
    0.53
    bs
    0.52
    de
    0.50
    z
    0.50
    fi
    0.49
    ged
    0.48
    line
    0.47
    ls
    0.46
    POSITIVE LOGITS
     हज़ार
    0.69
    บุรี
    0.53
    ਕਾਰ
    0.51
    郢
    0.51
     incroyable
    0.50
    รัฐ
    0.49
    ราม
    0.49
    镞
    0.48
    म्
    0.47
     surve
    0.47
    Activations Density 0.000%

    No Known Activations