© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1310
    Prev
    Next
    INDEX
    Explanations

    ethical manner, good resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    être
    0.79
    стов
    0.78
    鎌
    0.73
    лос
    0.72
    𝒔
    0.71
    autorisation
    0.71
    cym
    0.70
    姿
    0.70
    ㄜ
    0.70
    со
    0.69
    POSITIVE LOGITS
    เมื่อ
    0.88
    เริ่ม
    0.86
     společnost
    0.84
     stále
    0.80
     relazioni
    0.79
     ጋር
    0.77
     continuamente
    0.77
     trata
    0.75
    टरनेट
    0.75
     eerder
    0.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.