© 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. 51345
    Prev
    Next
    INDEX
    Explanations

    set up a field goal

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

    content structure and SEO

    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
    v
    0.57
     S
    0.54
     Resources
    0.52
    S
    0.50
     Fin
    0.50
     Letters
    0.50
     Steering
    0.49
     Eds
    0.49
     It
    0.48
     IM
    0.48
    POSITIVE LOGITS
    谟
    0.55
    pendiente
    0.53
    ريم
    0.51
    Hemos
    0.50
     gekommen
    0.50
     اولمپس
    0.49
    ManagerPortal
    0.49
     만큼
    0.48
     artificielle
    0.47
    Penumpang
    0.47
    Activations Density 0.000%

    No Known Activations