© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199744
    Prev
    Next
    INDEX
    Explanations

    placeholderterror

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flyer
    0.49
     FAQ
    0.47
     goodwill
    0.47
     праців
    0.46
     й
    0.45
     पूल
    0.44
     freeway
    0.43
     ф
    0.43
     త
    0.43
     rugby
    0.42
    POSITIVE LOGITS
    iams
    0.47
     estruturas
    0.45
    ја
    0.45
     estructuras
    0.45
     aconsel
    0.44
     vazio
    0.44
     vuole
    0.43
     gönd
    0.43
    ipot
    0.43
    image
    0.42
    Activations Density 0.006%

    No Known Activations