© 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. 22-GEMMASCOPE-2-RES-16K
    7. 3466
    Prev
    Next
    INDEX
    Explanations

    summarize

    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
    tering
    0.96
    érance
    0.85
    ance
    0.84
    iencia
    0.82
    ランス
    0.82
    щие
    0.82
     thrift
    0.81
    梏
    0.81
    alty
    0.80
    ancy
    0.80
    POSITIVE LOGITS
     process
    0.71
     Big
    0.66
     Al
    0.65
     Process
    0.64
     알
    0.64
     al
    0.63
     pe
    0.63
     Sam
    0.63
     proces
    0.62
    알
    0.62
    Activations Density 0.156%

    No Known Activations