© 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. 168841
    Prev
    Next
    INDEX
    Explanations

    invitations, terminated, experiment

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

    fully polished, tested thoroughly, rarely successful

    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
    hank
    0.48
    imaging
    0.46
    mck
    0.46
     തോ
    0.45
    emonic
    0.44
    បង្ហ
    0.44
    <unused260>
    0.44
    <unused423>
    0.44
    రకు
    0.44
    ৬
    0.43
    POSITIVE LOGITS
    OPS
    0.47
     .
    0.46
    ﺒ
    0.46
    
    0.46
     (
    0.45
    ERT
    0.45
    ﺘ
    0.45
    ޙ
    0.45
     dụ
    0.45
    ﺤ
    0.45
    Activations Density 0.000%

    No Known Activations