© 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. 3354
    Prev
    Next
    INDEX
    Explanations

    philosophical questions and perspectives

    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
    হের
    1.96
     ​​
    1.87
    য়ের
    1.86
     держа
    1.84
    gly
    1.78
    undi
    1.73
    odils
    1.69
     女
    1.68
    roquois
    1.67
    ridine
    1.66
    POSITIVE LOGITS
    ᴛ
    2.37
    𝑡
    2.36
    
    2.33
    𝚝
    2.33
    antial
    2.30
    𝗍
    2.25
    𝚖
    2.23
    𝑢
    2.22
    ोनेशिया
    2.22
    𝗮
    2.19
    Activations Density 0.025%

    No Known Activations