© 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. 154768
    Prev
    Next
    INDEX
    Explanations

    electronic contact

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

    a national commission

    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
     проє
    0.51
    their
    0.46
    modations
    0.46
     legible
    0.45
     supportive
    0.44
    🙏🏻
    0.44
    seiten
    0.43
     reais
    0.42
    𝗦
    0.42
    residual
    0.41
    POSITIVE LOGITS
     জগতে
    0.51
     giết
    0.49
    یتی
    0.49
     Trier
    0.46
     Paradigm
    0.44
     কারণে
    0.44
     Spins
    0.44
     হাত
    0.43
     Isolated
    0.43
     eliminar
    0.43
    Activations Density 0.001%

    No Known Activations