© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2280
    Prev
    Next
    INDEX
    Explanations

    harm, product, and their causes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
    占据
    0.72
     tweaks
    0.70
    変更
    0.67
    えず
    0.67
     tweak
    0.67
     impacting
    0.65
    挠
    0.65
    خذ
    0.64
    stelling
    0.63
    とりあえず
    0.63
    POSITIVE LOGITS
     caused
    1.42
    caused
    1.25
     triggered
    1.15
     associated
    1.13
     induced
    1.05
     provoked
    1.02
     CAUSED
    0.99
     occasioned
    0.98
     resulting
    0.97
     выз
    0.96
    Activations Density 0.967%

    No Known Activations