© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42965
    Prev
    Next
    INDEX
    Explanations

    what follows certain words

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

    creating or portraying

    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
    xt
    0.47
    heli
    0.47
     cond
    0.46
    ۔
    0.46
    user
    0.46
    original
    0.45
    fert
    0.45
    opt
    0.45
    cond
    0.44
    foreign
    0.43
    POSITIVE LOGITS
     BLOG
    0.57
    ༧
    0.57
     말미암
    0.55
     COMMUNITY
    0.54
     lập
    0.54
     должность
    0.53
     DAVIS
    0.52
     délégation
    0.52
     associée
    0.50
     CHILD
    0.50
    Activations Density 0.000%

    No Known Activations