© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5179
    Prev
    Next
    INDEX
    Explanations

    here's a guide

    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_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
     painful
    0.96
    窃
    0.79
     photoc
    0.78
     reprodu
    0.76
     ihres
    0.74
    数
    0.71
     Punkte
    0.71
     conse
    0.71
     数
    0.71
     difficultés
    0.71
    POSITIVE LOGITS
     exists
    0.82
     is
    0.74
     will
    0.74
     provides
    0.74
    是一個
    0.70
    オー
    0.69
     разработан
    0.67
    是一款
    0.66
     employs
    0.65
     проводится
    0.65
    Activations Density 0.078%

    No Known Activations