© 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. 3804
    Prev
    Next
    INDEX
    Explanations

    core principles violated

    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
     संप
    0.70
     copper
    0.69
    累積
    0.67
    હુ
    0.67
    Ign
    0.67
     underestimated
    0.66
     mom
    0.65
    銹
    0.65
     Californians
    0.65
    잊
    0.65
    POSITIVE LOGITS
     central
    0.77
     hallmark
    0.77
     blatant
    0.74
     ciri
    0.73
     direct
    0.67
     सख्ती
    0.67
    明显
    0.66
     intentional
    0.66
     parody
    0.66
     defining
    0.65
    Activations Density 0.596%

    No Known Activations