© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11273
    Prev
    Next
    INDEX
    Explanations

    white, especially in racial contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیا۔
    1.44
    صار
    1.40
    افل
    1.40
     unsurpassed
    1.39
    вичайно
    1.39
    炲
    1.39
    োজেন
    1.38
    жил
    1.38
    ivamente
    1.36
    azd
    1.35
    POSITIVE LOGITS
     agak
    1.70
     (~
    1.69
     reprieve
    1.67
     (?)
    1.65
    (?)
    1.65
     tweaks
    1.65
     sprinkles
    1.64
    tmp
    1.62
    bak
    1.61
     backstory
    1.59
    Activations Density 0.870%

    No Known Activations