© 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. 92203
    Prev
    Next
    INDEX
    Explanations

    Executive Order, restoration, skill, asthma

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

    old ways or collaboration

    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
    зой
    0.44
     Gets
    0.43
     Wars
    0.41
     Colon
    0.41
    ijnlijk
    0.41
    爵
    0.41
     Mort
    0.41
    丰富
    0.40
     Nomin
    0.40
     страш
    0.40
    POSITIVE LOGITS
     koperasi
    0.46
    ،
    0.46
     develop
    0.46
    /∂
    0.46
     fornece
    0.46
     vidas
    0.45
     mengajak
    0.44
     membangun
    0.44
     eliminate
    0.43
    ດ້
    0.42
    Activations Density 0.001%

    No Known Activations