© 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. 11605
    Prev
    Next
    INDEX
    Explanations

    caching

    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
    eme
    2.51
    vrd
    2.27
    <bos>
    2.25
    ہی
    2.21
    
    2.14
    ھی
    2.10
    خب
    2.07
     домаћинствима
    2.06
    д
    2.05
    rar
    2.05
    POSITIVE LOGITS
     llave
    2.89
     montagna
    2.88
    ানা
    2.84
    ယ်
    2.69
    ဲ
    2.57
    മെ
    2.55
    ంధ్ర
    2.53
    oqu
    2.53
    ITATE
    2.52
     плате
    2.52
    Activations Density 0.003%

    No Known Activations