© 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. 178814
    Prev
    Next
    INDEX
    Explanations

    outstanding moments

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

    expertise underestimate

    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
     proveedores
    0.48
    dataProvider
    0.45
     escrow
    0.44
     leistungs
    0.44
     역할
    0.43
     في
    0.43
    の
    0.42
    업
    0.41
     in
    0.41
     domanda
    0.41
    POSITIVE LOGITS
     Canoe
    0.50
    ไม่ได้
    0.46
    rą
    0.45
    两位
    0.45
    เพื่อให้
    0.45
    SA
    0.44
     seemed
    0.44
     Aloha
    0.43
    ellow
    0.43
    okat
    0.43
    Activations Density 0.001%

    No Known Activations