© 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. 2251
    Prev
    Next
    INDEX
    Explanations

    credit card

    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
     discontinuous
    0.81
    cong
    0.75
     Founders
    0.65
    ē
    0.61
    gga
    0.61
     Sling
    0.60
     कैंसिल
    0.59
    isPresent
    0.59
    venv
    0.59
    फा
    0.58
    POSITIVE LOGITS
    瑩
    0.64
     model
    0.61
     elicit
    0.59
     elic
    0.58
     ions
    0.56
     có
    0.56
     ormai
    0.56
    nic
    0.55
     sounding
    0.55
     herb
    0.55
    Activations Density 0.211%

    No Known Activations