© 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. 11642
    Prev
    Next
    INDEX
    Explanations

    tagsattribute in html or vue

    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
    बॉ
    1.71
     recordando
    1.58
    Specs
    1.53
     impresionante
    1.52
    Pictures
    1.51
    рожден
    1.49
    u
    1.49
    Flipper
    1.48
    Коммента
    1.46
     muchachos
    1.45
    POSITIVE LOGITS
    ᅮ
    1.51
    ፡
    1.51
     ਕੇ
    1.48
    ᅵ
    1.46
     ਰਾ
    1.44
    ូច
    1.43
    ιος
    1.42
     광
    1.36
    日在
    1.36
    monary
    1.35
    Activations Density 0.000%

    No Known Activations