© 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. 253620
    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
    酬
    0.45
    prd
    0.44
     SPD
    0.42
    苑
    0.41
     процесс
    0.41
     सिन
    0.40
     lysate
    0.39
     festivals
    0.39
    .**
    0.39
    酩
    0.39
    POSITIVE LOGITS
    ية
    0.47
     துரு
    0.47
    éder
    0.45
     pousse
    0.45
     Forrest
    0.45
    ہ
    0.45
     Constantinople
    0.43
    și
    0.43
    함
    0.43
    omegranate
    0.42
    Activations Density 0.001%

    No Known Activations