© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 252061
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tensor
    0.60
     milites
    0.48
     무
    0.48
     Wirkung
    0.47
     Airbus
    0.46
     Status
    0.46
     virtu
    0.46
     Kanal
    0.45
     Luft
    0.44
     Effects
    0.44
    POSITIVE LOGITS
     ਜਾਣ
    0.46
    ষুধ
    0.45
    नु
    0.43
    Fruits
    0.43
     ഭക്ഷ
    0.43
    ('|
    0.43
    ଷ
    0.43
    Serializable
    0.42
    apeake
    0.42
     wages
    0.42
    Activations Density 0.003%

    No Known Activations