© 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. 132464
    Prev
    Next
    INDEX
    Explanations

    Churches, benefits, recovery, threatened

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

    of, in, to

    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
    ursed
    0.50
    URS
    0.49
     |
    0.49
     expenditures
    0.49
    🛣
    0.48
     recombin
    0.48
     급
    0.47
     vehicles
    0.45
     contingencies
    0.45
    🍲
    0.45
    POSITIVE LOGITS
    び
    0.50
    羅
    0.46
    वाने
    0.45
    ána
    0.44
    則
    0.44
    向
    0.43
    としても
    0.42
    checkmark
    0.42
    詔
    0.42
    療法
    0.42
    Activations Density 0.000%

    No Known Activations