© 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. 66085
    Prev
    Next
    INDEX
    Explanations

    offers selection

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

    safety pins

    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
     disent
    0.45
     بالإضافة
    0.45
    :
    0.41
    Additionally
    0.39
     Additionally
    0.39
     देखना
    0.38
     correspondingly
    0.38
     motorized
    0.38
    Calculating
    0.38
    到时候
    0.38
    POSITIVE LOGITS
    フォーマンス
    0.47
    ？”
    0.47
    ？
    0.46
    x
    0.45
    товые
    0.44
    हिर
    0.44
     социальной
    0.44
     emociones
    0.44
    ントン
    0.43
    ？）
    0.43
    Activations Density 0.006%

    No Known Activations