© 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. 613
    Prev
    Next
    INDEX
    Explanations

    section headings starting with 1

    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
     also
    0.57
    こともある
    0.56
     stesso
    0.54
     régulière
    0.51
     {:.
    0.51
    трите
    0.50
     likewise
    0.50
     تمام
    0.50
    ूँगा
    0.49
    なくても
    0.49
    POSITIVE LOGITS
    ️⃣
    1.08
    ⃣
    0.96
    :
    0.95
    .
    0.92
    )
    0.89
    rd
    0.87
    ：
    0.83
    nd
    0.83
    b
    0.82
    0
    0.81
    Activations Density 0.819%

    No Known Activations