© 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. 51577
    Prev
    Next
    INDEX
    Explanations

    amusement, about, Adams, was, deliver, Understanding, pursue

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

    coli, fiber, lithium, colonization

    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
     наре
    0.53
    ziest
    0.53
     ряда
    0.51
     доклад
    0.49
     написа
    0.49
    郧
    0.48
    iskup
    0.47
    senior
    0.47
     શરૂ
    0.47
     ജോ
    0.47
    POSITIVE LOGITS
     ACL
    0.52
     rebell
    0.51
     IOException
    0.49
     symbi
    0.47
     growth
    0.47
     ACH
    0.47
     exile
    0.46
     ZnO
    0.46
    ؤ
    0.46
    ير
    0.46
    Activations Density 0.001%

    No Known Activations