© 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. 90647
    Prev
    Next
    INDEX
    Explanations

    data subject rights and consent

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

    specific concepts

    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
     Lalu
    0.48
     draining
    0.47
     poi
    0.46
     A
    0.45
     lalu
    0.44
     manteniendo
    0.44
     н
    0.43
     fractionation
    0.43
     dopo
    0.42
    หลังจาก
    0.42
    POSITIVE LOGITS
    ΤΑ
    0.47
     ఇందు
    0.45
    engin
    0.44
    СТЕ
    0.43
    úncia
    0.43
    юсь
    0.43
    SignUp
    0.42
    ΜΑ
    0.41
    鏡
    0.41
    最具
    0.41
    Activations Density 0.003%

    No Known Activations