© 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. 51128
    Prev
    Next
    INDEX
    Explanations

    kids, guys, dudes, stuff

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

    vibe

    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
    Y
    1.38
    R
    1.29
    X
    1.28
    M
    1.25
    V
    1.23
    the
    1.22
    A
    1.18
    P
    1.16
    L
    1.15
    H
    1.13
    POSITIVE LOGITS
    ’
    1.01
     أجل
    0.88
    يل
    0.85
    ไหน
    0.84
     baddies
    0.84
     الناس
    0.80
     matchups
    0.79
     люди
    0.77
    กัน
    0.77
     самых
    0.76
    Activations Density 0.244%

    No Known Activations