© 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. 155083
    Prev
    Next
    INDEX
    Explanations

    last debate

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

    first move

    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
    อรี่
    0.50
    霊
    0.47
    ли
    0.46
    อน
    0.46
    ॉय
    0.45
    IZ
    0.43
    িল
    0.43
    が悪
    0.43
    IONES
    0.42
    RIES
    0.42
    POSITIVE LOGITS
     CGM
    0.46
     Hü
    0.46
     ١
    0.45
     prolet
    0.44
     enfrenta
    0.43
    obranch
    0.43
     PSG
    0.42
     confront
    0.42
     Atelier
    0.41
     extracting
    0.41
    Activations Density 0.001%

    No Known Activations