© 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. 3371
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
    বীন্দ্রনাথ
    2.40
    بال
    2.31
    躇
    2.30
    琲
    2.27
    piar
    2.26
    猬
    2.22
    produkt
    2.16
    pi
    2.14
    ։
    2.05
    бу
    2.03
    POSITIVE LOGITS
    esse
    2.99
    ières
    2.91
    ா
    2.84
     întâ
    2.81
    ﮄ
    2.79
    AWSJavaScriptSDK
    2.78
    Bbb
    2.77
    𝙩
    2.74
    netje
    2.72
    chod
    2.71
    Activations Density 0.231%

    No Known Activations