© 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. 4829
    Prev
    Next
    INDEX
    Explanations

    if you, no

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

    sulfuric acid and acids

    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
    -
    0.53
     Kush
    0.49
     Vans
    0.48
    heen
    0.47
     Propulsion
    0.45
     Harman
    0.45
    oulli
    0.44
     streetlight
    0.44
     Marcy
    0.44
    ush
    0.44
    POSITIVE LOGITS
    ($('#
    0.53
     alfabet
    0.53
     estilos
    0.50
    alma
    0.49
    library
    0.49
    นิด
    0.49
    ේද
    0.48
     regista
    0.47
    HANDLE
    0.47
    driver
    0.47
    Activations Density 0.000%

    No Known Activations