© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 168839
    Prev
    Next
    INDEX
    Explanations

    one ruler

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

    analog, flaws, imbalance, moments

    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
    Zinc
    0.59
     Vee
    0.49
     a
    0.48
    Acetic
    0.47
     Geet
    0.46
    めた
    0.46
    تقدم
    0.45
    ZnO
    0.45
     an
    0.45
     stoichi
    0.44
    POSITIVE LOGITS
    illeurs
    0.54
    鞑
    0.54
     partisans
    0.52
     laisser
    0.52
     প্রণাম
    0.46
    하라
    0.44
     accents
    0.43
    existence
    0.43
     illusions
    0.42
     photons
    0.42
    Activations Density 0.001%

    No Known Activations