© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15681
    Prev
    Next
    INDEX
    Explanations

    asking you to do illegal things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     flatten
    1.29
    Quite
    1.27
     evacuate
    1.26
     ridurre
    1.21
     retirar
    1.19
     escalate
    1.18
     পরিত্র
    1.17
    畱
    1.17
     incrementar
    1.16
    łu
    1.16
    POSITIVE LOGITS
     eigener
    1.04
     WI
    1.03
     характер
    1.03
     जिसके
    1.02
     отношении
    1.02
     כך
    0.99
     against
    0.98
     характера
    0.98
     местности
    0.97
     juris
    0.96
    Activations Density 0.159%

    No Known Activations