© 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. 216745
    Prev
    Next
    INDEX
    Explanations

    places and things

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

    often associated with

    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
     schwarz
    0.46
     thomas
    0.45
    Technische
    0.45
    isers
    0.44
    矫
    0.43
    Thomas
    0.43
    $-
    0.43
    nacht
    0.42
    km
    0.42
     soluciones
    0.41
    POSITIVE LOGITS
    埼玉
    0.48
     addressed
    0.45
     danh
    0.44
    ρω
    0.43
    広島
    0.43
    ше
    0.43
    मोट
    0.43
     आवड
    0.42
     inol
    0.41
    酩
    0.41
    Activations Density 0.000%

    No Known Activations