© 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. 67903
    Prev
    Next
    INDEX
    Explanations

    various sites

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

    responsible for, legacy, dedicated host, prophecy, golden cross

    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
     bestimmten
    0.49
     bijzonder
    0.49
    出
    0.48
    ари
    0.48
    ců
    0.47
     بي
    0.46
    бно
    0.46
    定
    0.46
    𝐞
    0.45
    или
    0.44
    POSITIVE LOGITS
     armada
    0.55
     cartons
    0.52
    買った
    0.50
    ဢ
    0.50
     McE
    0.49
     मम्मी
    0.49
     cartera
    0.48
     sequencing
    0.47
     tattoos
    0.47
     KFC
    0.47
    Activations Density 0.000%

    No Known Activations