© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 791
    Prev
    Next
    INDEX
    Explanations

    being evil

    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_7_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
     provavelmente
    1.33
     mengak
    1.14
    سى
    1.13
     विरुद्ध
    1.12
    }^{-}$
    1.12
     disciplinas
    1.10
    etlen
    1.09
     generalmente
    1.09
     probabilmente
    1.09
     probablemente
    1.09
    POSITIVE LOGITS
    [^
    0.83
     №
    0.80
    heastern
    0.80
    uccino
    0.76
     window
    0.76
     ?>
    0.75
    xiety
    0.74
    ><?
    0.74
     Happy
    0.74
    ाब
    0.74
    Activations Density 0.545%

    No Known Activations