© 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. 62538
    Prev
    Next
    INDEX
    Explanations

    regional head, facebook, carpenter

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

    describing processes and outcomes

    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
     briefings
    0.49
     operators
    0.44
     Generic
    0.41
    vens
    0.41
     bullies
    0.40
     wards
    0.40
    钀
    0.40
    бу
    0.40
     Corporation
    0.40
     Theatre
    0.40
    POSITIVE LOGITS
    ঠোর
    0.47
     مؤرشف
    0.45
    郵
    0.44
     पोकेमॉन
    0.44
    toJSON
    0.44
    installment
    0.44
    tareas
    0.44
     মোটরসাই
    0.44
    地铁
    0.43
    ట్స్‌మన్
    0.43
    Activations Density 0.000%

    No Known Activations