© 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. 5396
    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
     仕事
    0.46
    Ꮦ
    0.46
    Duz
    0.46
     puriso
    0.46
    LOCAL
    0.45
    т
    0.45
     zmdi
    0.45
    ත
    0.45
    ොර
    0.45
    젓
    0.45
    POSITIVE LOGITS
    of
    0.50
     stressed
    0.47
     fielded
    0.47
     choosing
    0.46
     eroded
    0.43
     esche
    0.43
    fee
    0.43
     thicken
    0.43
     whistling
    0.42
     অঙ্ক
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.