© 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. 22-GEMMASCOPE-2-RES-16K
    7. 5168
    Prev
    Next
    INDEX
    Explanations

    medical advice

    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
    枋
    0.73
    igual
    0.71
    梠
    0.71
     Agricultural
    0.70
     technically
    0.70
     incumbents
    0.70
    Trades
    0.69
    ക്കായി
    0.69
     መስ
    0.69
    attacking
    0.68
    POSITIVE LOGITS
    esor
    0.75
    한
    0.74
     katanya
    0.73
     প্রশ্নের
    0.72
     vrouwen
    0.72
     Из
    0.72
     femmes
    0.70
    從
    0.67
    頓
    0.67
    cion
    0.67
    Activations Density 0.020%

    No Known Activations