© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13817
    Prev
    Next
    INDEX
    Explanations

    mitigation of risks and harms

    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
    犮
    2.85
    contrar
    2.80
    ंपरा
    2.79
     trabal
    2.76
    ियोजना
    2.72
    ल्याण
    2.69
    ские
    2.69
    ীয়
    2.69
    liness
    2.68
     organelles
    2.64
    POSITIVE LOGITS
    s
    4.01
     ​​
    2.40
    i
    2.36
    CCO
    2.36
    יא
    2.33
    V
    2.30
    ات
    2.29
    tors
    2.28
    tang
    2.18
    ి
    2.17
    Activations Density 0.021%

    No Known Activations