© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6556
    Prev
    Next
    INDEX
    Explanations

    Human feedback HELP

    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
     scarred
    0.83
    𝔬
    0.78
     stripped
    0.76
     diary
    0.75
     plotter
    0.74
     cafeteria
    0.73
    গ্রাফ
    0.72
     cath
    0.72
     Palestinian
    0.71
     mấy
    0.71
    POSITIVE LOGITS
    ricane
    0.85
    setText
    0.72
     R
    0.70
     retain
    0.69
     replace
    0.68
    넣
    0.68
     lä
    0.68
     공급
    0.68
     提供
    0.67
    ())
    0.66
    Activations Density 0.010%

    No Known Activations