© 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. 240884
    Prev
    Next
    INDEX
    Explanations

    resizable, inscription, paying, show you

    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
     Dime
    0.50
     (
    0.48
     obtains
    0.45
     Ju
    0.45
     ն
    0.44
     ஒ
    0.44
     intestate
    0.43
     собственной
    0.43
     Obt
    0.43
     र
    0.42
    POSITIVE LOGITS
    MBOL
    0.58
    Hasil
    0.53
    Serbia
    0.53
    Brown
    0.52
    Museum
    0.50
    Dramatic
    0.50
    Alpine
    0.50
    Hannah
    0.49
    Mountains
    0.49
    Mere
    0.48
    Activations Density 0.000%

    No Known Activations