© 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. 177471
    Prev
    Next
    INDEX
    Explanations

    mobile phone

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

    learning and evolving systems

    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
    CEO
    0.47
    τίας
    0.46
    BOSTON
    0.46
     CEOs
    0.45
    ᇁ
    0.45
    kého
    0.44
    demand
    0.43
    達
    0.43
    mean
    0.42
    mj
    0.42
    POSITIVE LOGITS
     misfort
    0.47
     saben
    0.47
    CallSettings
    0.46
    راق
    0.43
     அவ
    0.43
     Killer
    0.42
     اسرائیل
    0.41
     Difer
    0.41
     suger
    0.41
     contened
    0.41
    Activations Density 0.000%

    No Known Activations