© 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. 4255
    Prev
    Next
    INDEX
    Explanations

    physical sensations

    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
     moment
    0.76
    ?}",
    0.74
    zoned
    0.71
     moments
    0.67
     atmósfera
    0.65
     Atmosphäre
    0.65
     solemnly
    0.64
     Moment
    0.62
    enciaga
    0.62
     momento
    0.62
    POSITIVE LOGITS
     ع
    0.78
    butterfly
    0.71
     целый
    0.69
    ortex
    0.68
     Wild
    0.68
     native
    0.67
     Bile
    0.67
    Bil
    0.67
     SHER
    0.66
     স্বেচ্ছাসেব
    0.66
    Activations Density 0.144%

    No Known Activations