© 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. 257900
    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
    ذي
    0.53
    笂
    0.53
    ერ
    0.53
    ლებიც
    0.51
     primjer
    0.50
    т
    0.50
    𐱅
    0.49
    วย
    0.48
    টেড
    0.48
    ריה
    0.48
    POSITIVE LOGITS
    is
    0.61
    arid
    0.57
    on
    0.55
    ag
    0.54
    ession
    0.52
    are
    0.52
    1
    0.52
     Addis
    0.50
    anto
    0.49
    0
    0.49
    Activations Density 0.000%

    No Known Activations