© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 133563
    Prev
    Next
    INDEX
    Explanations

    books, where, at, so

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

    online platforms

    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
    k
    0.55
    t
    0.53
     occupants
    0.50
     potentials
    0.50
     residents
    0.49
     punishments
    0.48
    :
    0.48
    ardin
    0.48
    on
    0.47
    y
    0.47
    POSITIVE LOGITS
     Fluent
    0.54
     Кали
    0.50
     Compost
    0.49
     Hemos
    0.47
     Primeira
    0.47
     सुनाई
    0.47
     परिचित
    0.46
     UTI
    0.46
     História
    0.46
     Universidade
    0.45
    Activations Density 0.000%

    No Known Activations