© 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. 63587
    Prev
    Next
    INDEX
    Explanations

    highest rate, newest, fragment, ordering

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

    focus on

    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
    Negative Logits
     Μα
    0.47
     Orbital
    0.47
     对
    0.46
    াউ
    0.44
    attiyam
    0.44
     Ultrasonic
    0.44
    Manufact
    0.43
    嬠
    0.43
     დარ
    0.43
     হুম
    0.43
    POSITIVE LOGITS
     nossos
    0.56
     demoral
    0.47
     наших
    0.46
     injustices
    0.46
    日本では
    0.46
     entrepreneurs
    0.45
     monies
    0.45
     unequivocally
    0.45
     naszych
    0.44
     nostri
    0.44
    Activations Density 0.000%

    No Known Activations