© 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. 5450
    Prev
    Next
    INDEX
    Explanations

    customers, visitors, gain, real, lose

    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
     uniquely
    0.98
    unique
    0.97
     соотно
    0.91
    stead
    0.88
     ইউনিক
    0.87
    λον
    0.87
    $+
    0.86
     اسی
    0.85
    ěn
    0.84
    $/
    0.84
    POSITIVE LOGITS
     einer
    0.74
    ची
    0.69
     bir
    0.66
    一看
    0.64
     vode
    0.64
     eine
    0.64
     index
    0.63
     medy
    0.63
     cure
    0.63
     une
    0.62
    Activations Density 0.000%

    No Known Activations