© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 227013
    Prev
    Next
    INDEX
    Explanations

    critic, surprises, difference, recorder, seen

    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
     adjuvant
    0.55
     cytosolic
    0.55
     elution
    0.52
     sulit
    0.49
    larini
    0.49
    の問題
    0.47
     systematics
    0.47
    𐱃
    0.47
     perturbations
    0.46
     aberrant
    0.46
    POSITIVE LOGITS
    ána
    0.49
     जोड़ों
    0.48
     टेली
    0.47
     吉
    0.46
    酰
    0.46
     条
    0.46
    絮
    0.46
    isher
    0.46
     林
    0.46
    测
    0.44
    Activations Density 0.000%

    No Known Activations