© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2978
    Prev
    Next
    INDEX
    Explanations

    `enum`, `class`, `$OPTARG`

    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_17_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
    இ
    0.85
     Perception
    0.83
     Timeline
    0.82
     Occupation
    0.80
     👌
    0.79
     -
    0.79
     .
    0.76
     PER
    0.76
     )
    0.75
     ।
    0.75
    POSITIVE LOGITS
     competitively
    0.68
     statically
    0.67
     dipping
    0.67
    <0xE8>
    0.67
    MRC
    0.66
    τρ
    0.66
     ankles
    0.65
     CBI
    0.64
    ù
    0.64
     moss
    0.64
    Activations Density 0.274%

    No Known Activations