© 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. 192335
    Prev
    Next
    INDEX
    Explanations

    vaccination should be completed

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

    creating objects or describing actions

    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
    स्तिक
    0.44
    isHidden
    0.43
    voer
    0.41
    oldCount
    0.40
    bol
    0.40
    涪
    0.40
    sächlich
    0.39
     więcej
    0.39
    nobyl
    0.39
    합
    0.39
    POSITIVE LOGITS
     දී
    0.47
    cı
    0.45
     परिश
    0.45
    ēl
    0.45
     સ
    0.44
     graduated
    0.42
     पॅ
    0.42
     catalyzed
    0.42
     proffered
    0.42
    أ
    0.42
    Activations Density 0.000%

    No Known Activations