© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13146
    Prev
    Next
    INDEX
    Explanations

    with difficult news

    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_13_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
     Projeto
    1.02
     सरस्वती
    1.00
    Projeto
    0.99
    Pink
    0.99
    UsedError
    0.97
    <unused292>
    0.97
    Sicilian
    0.95
    Decor
    0.93
    Resposta
    0.93
     kusal
    0.92
    POSITIVE LOGITS
     highest
    0.74
    ↵↵
    0.73
     [
    0.73
     points
    0.67
     persuaded
    0.66
     panel
    0.65
    liche
    0.65
     development
    0.64
     looming
    0.64
     layer
    0.64
    Activations Density 0.001%

    No Known Activations