© 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. 200339
    Prev
    Next
    INDEX
    Explanations

    managed in-rush

    np_acts-logits-general · gemini-2.5-flash-lite

    Vanishing/exploding gradients

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     نوم
    0.48
    غب
    0.47
    équation
    0.45
    سمى
    0.44
    subplot
    0.43
    قى
    0.43
    <0x0C>
    0.43
     prototyp
    0.43
    linewidth
    0.43
     itinéraires
    0.43
    POSITIVE LOGITS
     ',
    0.51
    চ্ছেন
    0.51
     SET
    0.50
     jų
    0.49
    ப்படுத்து
    0.48
     TESTING
    0.48
    RAL
    0.46
     לה
    0.45
    ٬
    0.45
    SET
    0.44
    Activations Density 0.000%

    No Known Activations