© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 11731
    Prev
    Next
    INDEX
    Explanations

    encourage or discourage behavior indirectly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    冊
    0.84
    templates
    0.76
     automobiles
    0.71
    ス
    0.70
     matri
    0.69
     управля
    0.67
    와이스
    0.66
     управ
    0.66
     Chiến
    0.66
    勋
    0.66
    POSITIVE LOGITS
     deterred
    1.35
     discouraged
    1.28
     discour
    1.22
     discouraging
    1.20
     discourage
    1.20
     incentive
    1.18
     entice
    1.11
     encourage
    1.10
     dissu
    1.09
     encourages
    1.08
    Activations Density 0.191%

    No Known Activations