© 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. 257011
    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
     যৌ
    0.44
    is
    0.44
    ozz
    0.43
    uzz
    0.41
    uzzles
    0.40
    ẵn
    0.40
    <0xD8>
    0.39
    㨁
    0.39
    区的
    0.39
    䉽
    0.39
    POSITIVE LOGITS
    Լ
    0.46
    ست
    0.46
    чаем
    0.46
     senaste
    0.45
    ಿ
    0.45
    Latest
    0.45
    ล่าสุด
    0.44
    јан
    0.44
    閬
    0.44
    gató
    0.43
    Activations Density 0.001%

    No Known Activations