© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5687
    Prev
    Next
    INDEX
    Explanations

    Thank you

    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
    Coral
    0.95
     Coral
    0.83
     coral
    0.81
     Анто
    0.79
    日英
    0.78
     চন্দ্র
    0.76
     Ан
    0.76
    웡
    0.75
    coral
    0.74
     corals
    0.74
    POSITIVE LOGITS
     Bay
    0.75
    epin
    0.71
     San
    0.71
     Bancroft
    0.69
    apin
    0.67
     DMC
    0.67
    Bay
    0.66
     pyrite
    0.65
    మై
    0.64
     CHP
    0.62
    Activations Density 0.107%

    No Known Activations