© 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. 156090
    Prev
    Next
    INDEX
    Explanations

    Executive coach, metal lacquer, safe environment, priority

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

    integrated into, coffee shop, ArrayBuffer, indices

    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
    ہی
    0.67
    י
    0.52
    گ
    0.52
    ጀም
    0.51
    leave
    0.50
    एक
    0.50
    G
    0.48
     NATIONAL
    0.48
    NATIONAL
    0.47
     VISIT
    0.47
    POSITIVE LOGITS
    StringBuilder
    0.48
     Howard
    0.44
     ليست
    0.44
     skateboard
    0.42
     هذا
    0.42
    </strong>
    0.42
     storyteller
    0.42
     Ist
    0.42
     Yad
    0.41
     Lukas
    0.41
    Activations Density 0.000%

    No Known Activations