© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 200418
    Prev
    Next
    INDEX
    Explanations

    instructions starting with "use the"

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

    partial connection

    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
     предше
    0.49
     secara
    0.49
     diversa
    0.48
     colori
    0.47
     wyłącznie
    0.47
     منصوبہ
    0.46
     connues
    0.46
    珪
    0.46
     pantai
    0.45
     જતા
    0.45
    POSITIVE LOGITS
    ár
    0.50
     Ignite
    0.50
    is
    0.47
    ကြည့်
    0.47
    áj
    0.45
     Resonance
    0.45
    ijk
    0.45
    áb
    0.45
    ástica
    0.44
    iew
    0.44
    Activations Density 0.000%

    No Known Activations