© 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. 192353
    Prev
    Next
    INDEX
    Explanations

    new school, developed school

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

    various contexts often followed by specific types of words

    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
     Duo
    0.52
     MIMO
    0.52
    Group
    0.49
    
    0.49
    A
    0.47
    二人
    0.46
     solo
    0.45
     Rx
    0.45
     NaN
    0.45
     trainee
    0.45
    POSITIVE LOGITS
    час
    0.47
    ៦
    0.46
    㥉
    0.46
     sanctity
    0.46
    鸷
    0.46
    вить
    0.46
    笾
    0.46
    ൮
    0.46
    擄
    0.46
    સાર
    0.45
    Activations Density 0.001%

    No Known Activations