© 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. 64062
    Prev
    Next
    INDEX
    Explanations

    screen resolution

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

    **sleep**, **walking**, **build**, **Beginner**, **weekend**, **Software**

    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
     lenders
    0.50
    䣫
    0.47
     a
    0.45
     proport
    0.43
     lots
    0.43
     Banco
    0.43
     Lina
    0.42
     liens
    0.42
     assures
    0.42
    ル
    0.42
    POSITIVE LOGITS
    approach
    0.50
    }$&
    0.47
    有哪些
    0.46
    implemented
    0.46
    ajib
    0.45
    Received
    0.45
    planung
    0.45
    undle
    0.44
    approved
    0.44
    $[
    0.44
    Activations Density 0.000%

    No Known Activations