© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 104430
    Prev
    Next
    INDEX
    Explanations

    ,

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

    CLI, change, preferable

    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
    ERRORTYPE
    0.55
     gören
    0.48
     者
    0.47
     done
    0.44
    的情
    0.44
     görül
    0.43
    的地方
    0.43
     baku
    0.43
     galvanometer
    0.43
     gpointer
    0.43
    POSITIVE LOGITS
    How
    0.53
    Homework
    0.52
    ش
    0.52
    You
    0.51
    House
    0.50
    Colour
    0.49
    Who
    0.49
     Rings
    0.49
    Introducing
    0.49
    Get
    0.48
    Activations Density 0.001%

    No Known Activations