© 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. 254083
    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
    ע
    0.62
    い
    0.58
    ח
    0.55
    מע
    0.55
    ع
    0.55
    נו
    0.52
    כו
    0.51
    זו
    0.51
    맡
    0.51
    הר
    0.51
    POSITIVE LOGITS
     tooth
    0.47
     leftist
    0.46
     thug
    0.46
     तथ
    0.46
     लेकिन
    0.46
     ਜ
    0.45
    adh
    0.45
     တစ်
    0.45
     llegado
    0.45
     thread
    0.44
    Activations Density 0.000%

    No Known Activations