© 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. 255463
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    d
    1.22
    K
    1.09
    J
    0.95
    al
    0.90
    L
    0.90
    Q
    0.90
    Z
    0.87
    ០
    0.86
    F
    0.83
    inizi
    0.82
    POSITIVE LOGITS
     to
    1.20
    ку
    1.15
    ных
    1.15
     on
    1.13
    માં
    1.09
    ное
    1.05
    ной
    1.05
    هم
    1.05
    ن
    0.99
    !
    0.98
    Activations Density 0.175%

    No Known Activations