© 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. 255849
    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
    u
    0.68
    at
    0.60
    arm
    0.60
    en
    0.60
    ak
    0.56
    in
    0.55
    ag
    0.52
    uk
    0.52
    s
    0.52
    on
    0.51
    POSITIVE LOGITS
     apes
    0.53
    ші
    0.51
    ոչ
    0.48
     باپ
    0.48
     우리의
    0.47
    โปร
    0.47
     aplatis
    0.47
    เพ
    0.46
     peaks
    0.46
     drones
    0.46
    Activations Density 0.001%

    No Known Activations