© 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. 34687
    Prev
    Next
    INDEX
    Explanations

    current opportunities and technical terms

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

    outcomes and advancements

    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
    코
    0.52
    মে
    0.47
    мати
    0.45
    тан
    0.44
    ,~
    0.43
    urahan
    0.43
    배
    0.43
    霍
    0.43
    си
    0.43
    тинен
    0.43
    POSITIVE LOGITS
     EAG
    0.50
     forum
    0.50
     dvs
    0.49
     finns
    0.49
     heist
    0.49
     jest
    0.49
    jest
    0.47
     printf
    0.47
    ὑ
    0.46
     interdependent
    0.45
    Activations Density 0.001%

    No Known Activations