© 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. 6083
    Prev
    Next
    INDEX
    Explanations

    worth considering

    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
    strass
    0.73
     neatly
    0.70
     steps
    0.69
     thoughtfully
    0.69
     arithmetic
    0.68
    isierung
    0.68
    gments
    0.66
    滟
    0.65
     carefully
    0.65
     Abs
    0.64
    POSITIVE LOGITS
    while
    1.19
    जबकि
    0.98
     While
    0.90
    While
    0.89
     tandis
    0.84
     Considerable
    0.83
     எழுந்த
    0.81
     Significant
    0.80
     Noting
    0.80
     sedangkan
    0.79
    Activations Density 0.025%

    No Known Activations