© 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. 104939
    Prev
    Next
    INDEX
    Explanations

    after mass killings

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

    plans, write, develop

    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
    ที่คุณ
    0.45
     нагре
    0.45
    栝
    0.44
     вку
    0.44
     mempelajari
    0.43
    ңуз
    0.43
    oblast
    0.43
    癀
    0.42
    ण्ट
    0.42
    ElementType
    0.42
    POSITIVE LOGITS
    止
    0.45
     fathers
    0.45
    :
    0.45
     implements
    0.44
     tenements
    0.44
    和
    0.43
     riots
    0.43
     trac
    0.42
     books
    0.42
     explores
    0.42
    Activations Density 0.000%

    No Known Activations