© 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. 6522
    Prev
    Next
    INDEX
    Explanations

    resources for further learning

    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
     보통
    0.96
     주로
    0.91
     பொதுவாக
    0.90
     AUTHORS
    0.87
     halves
    0.84
    ពួកគេ
    0.83
    FZ
    0.81
    芓
    0.81
    របស់
    0.80
    ငန်း
    0.80
    POSITIVE LOGITS
    来说
    0.74
    มากมาย
    0.64
    來說
    0.61
    ?
    0.59
    []
    0.55
     reputable
    0.54
    (
    0.54
     comprob
    0.53
     ultima
    0.51
    ,
    0.51
    Activations Density 0.017%

    No Known Activations