© 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. 187319
    Prev
    Next
    INDEX
    Explanations

    the the

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

    human being

    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
     matériel
    0.48
    〠
    0.47
     표준
    0.47
     (“
    0.45
     gratu
    0.44
    ⸱
    0.44
     gönder
    0.43
    (“
    0.43
     bulletins
    0.43
     nauk
    0.43
    POSITIVE LOGITS
    ten
    0.51
    wearing
    0.50
    ম্বা
    0.49
    wise
    0.48
    ectable
    0.43
    arquia
    0.43
    <0x80>
    0.43
     دس
    0.43
    today
    0.43
    lendi
    0.43
    Activations Density 0.000%

    No Known Activations