© 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. 212841
    Prev
    Next
    INDEX
    Explanations

    Athens, people, us

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

    more formal phrasing

    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
     trib
    0.48
     मूल
    0.48
     α
    0.45
     Trib
    0.44
     tiếng
    0.43
     یور
    0.42
     முதலில்
    0.42
     син
    0.41
     Lawson
    0.41
     ██
    0.41
    POSITIVE LOGITS
    棗
    0.50
    具体的な
    0.49
     devast
    0.47
     stein
    0.46
     refresh
    0.46
    小時
    0.45
    refresh
    0.44
    賓
    0.43
    ទឹក
    0.43
    ស្ត
    0.43
    Activations Density 0.000%

    No Known Activations