© 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. 11157
    Prev
    Next
    INDEX
    Explanations

    Rate Limiting

    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
    𝘁
    3.46
    𝗸
    3.41
    𝘪
    3.24
    𝘴
    3.15
    𝗶
    3.15
    𝗹
    3.13
    𝗲
    3.08
    য়ের
    2.99
    ded
    2.99
    𝗴
    2.89
    POSITIVE LOGITS
    ו
    3.41
    ン
    3.40
    й
    3.12
    uwa
    3.01
    л
    2.99
    a
    2.95
    ে
    2.94
    एं
    2.91
    fini
    2.84
    ați
    2.80
    Activations Density 0.002%

    No Known Activations