© 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. 52178
    Prev
    Next
    INDEX
    Explanations

    solar flares and coronal plasma

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

    solar wind and magnetic aurora

    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
    执
    0.53
     Fundraising
    0.53
     时尚
    0.53
    须知
    0.52
    蒉
    0.52
    帼
    0.51
    蛔
    0.51
     अपार्टमेंट
    0.50
    谨慎
    0.50
    쁩
    0.50
    POSITIVE LOGITS
     coronal
    0.79
     plasmas
    0.78
     geomagnetic
    0.78
     plasma
    0.75
    plasma
    0.69
     solar
    0.68
     magnetic
    0.68
     chromosphere
    0.68
     chromospheric
    0.67
     filaments
    0.66
    Activations Density 0.027%

    No Known Activations