© 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. 17915
    Prev
    Next
    INDEX
    Explanations

    catalyzes, change, organizations, legal, children

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

    overcoming pornography and teens

    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
    ER
    0.48
    斯
    0.47
     postcss
    0.46
    ス
    0.45
     incluyendo
    0.42
    D
    0.42
    アル
    0.41
     voluptas
    0.41
     donning
    0.41
    ה
    0.40
    POSITIVE LOGITS
     doświad
    0.48
     strategi
    0.47
    人们
    0.44
     deği
    0.43
    <unused602>
    0.41
     ανθρώ
    0.41
     organizacji
    0.41
    никова
    0.40
     nonprofits
    0.39
     worldwide
    0.39
    Activations Density 0.189%

    No Known Activations