© 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. 210232
    Prev
    Next
    INDEX
    Explanations

    match.com to meet

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

    optimal threshold

    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
    s
    0.54
    t
    0.54
    tiene
    0.53
    d
    0.52
    larda
    0.50
     aparato
    0.49
    lara
    0.48
     Apparatus
    0.48
    县
    0.47
    ाह
    0.47
    POSITIVE LOGITS
    ꯤ
    0.45
     স্বভাব
    0.45
    ِ
    0.44
    вів
    0.43
     বলিউ
    0.42
     বিবাহের
    0.41
    Probit
    0.41
     لط
    0.41
     новий
    0.41
    acycl
    0.40
    Activations Density 0.000%

    No Known Activations