© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3176
    Prev
    Next
    INDEX
    Explanations

    findings and recommendations

    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
     tales
    0.71
     വിവ
    0.69
    PROGRAM
    0.69
     elution
    0.68
     stories
    0.66
    bait
    0.66
    ≡
    0.66
    的说
    0.63
     क्रांतिकार
    0.63
     কাশী
    0.63
    POSITIVE LOGITS
     ആണ്
    0.75
     menemukan
    0.74
     released
    0.73
     found
    0.73
     सर्क
    0.70
     брать
    0.68
     cuộc
    0.66
     الأخيرة
    0.65
    conduct
    0.65
     memer
    0.65
    Activations Density 0.158%

    No Known Activations