© 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. 157369
    Prev
    Next
    INDEX
    Explanations

    looking for specific things

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

    potential research jobs

    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
    स्थ
    0.49
     chan
    0.49
     *}$
    0.47
    aily
    0.45
    ousands
    0.45
    ান্ট
    0.45
     *
    0.45
     (!)
    0.44
    artment
    0.44
     foodstuffs
    0.44
    POSITIVE LOGITS
    ಾ
    0.54
    ონის
    0.48
    ہ
    0.48
    ോ
    0.46
    وہ
    0.44
    சிக்கும்
    0.44
    ز
    0.44
    ги
    0.44
    ის
    0.44
    <0xE4>
    0.44
    Activations Density 0.000%

    No Known Activations