© 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. 1173
    Prev
    Next
    INDEX
    Explanations

    notes and supplementary information

    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
    ¹
    0.70
    adiq
    0.66
    ❚
    0.64
    ²)
    0.64
    ^{+}\
    0.64
    ₂)
    0.63
    ²,
    0.63
    ²
    0.62
    borist
    0.61
     lebens
    0.61
    POSITIVE LOGITS
    Note
    1.08
    NOTE
    1.04
    Also
    1.03
    とても
    0.99
     Note
    0.97
     довольно
    0.96
     quite
    0.96
    Although
    0.96
    note
    0.95
    Whilst
    0.95
    Activations Density 1.249%

    No Known Activations