© 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. 71663
    Prev
    Next
    INDEX
    Explanations

    location, item, or entity followed by its state or relation

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

    but rather, bending, cools

    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
    旁边
    0.58
    ్రీన్
    0.53
    备份
    0.53
    或者是
    0.52
    菜单
    0.51
    术
    0.51
    回忆
    0.50
    季节
    0.49
    फोर
    0.48
     ออนไลน์
    0.48
    POSITIVE LOGITS
    an
    0.62
     amid
    0.57
     spearheaded
    0.55
     with
    0.52
     lured
    0.51
     from
    0.48
    amid
    0.47
     on
    0.46
     realizing
    0.46
    on
    0.46
    Activations Density 0.002%

    No Known Activations