© 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. 109536
    Prev
    Next
    INDEX
    Explanations

    can or should

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

    instructions and definitions

    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
     Kait
    0.46
     mab
    0.45
     E
    0.44
     actif
    0.42
     Lun
    0.41
     Laurent
    0.41
     Torque
    0.40
     accessory
    0.40
     Ferr
    0.39
     lai
    0.39
    POSITIVE LOGITS
     bureaucratic
    0.50
     bureaucr
    0.48
    umumkan
    0.47
     подготовке
    0.45
    غرافيا
    0.44
    酝
    0.44
     этом
    0.44
    prepare
    0.44
     आयोजित
    0.44
     melakukannya
    0.43
    Activations Density 0.002%

    No Known Activations