© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13095
    Prev
    Next
    INDEX
    Explanations

    generating images

    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
    あげ
    1.07
     fondée
    1.02
     இறு
    0.98
    ব্যব
    0.94
    ‘
    0.92
    Ề
    0.91
    ルトラ
    0.90
    Õ
    0.89
    거
    0.89
    ções
    0.88
    POSITIVE LOGITS
     هنگام
    1.47
    notification
    1.46
    ﺖ
    1.43
    ﻄ
    1.41
    </table>
    1.37
     wanneer
    1.35
    npm
    1.35
    ﻂ
    1.30
     randomNumber
    1.29
     tijdens
    1.28
    Activations Density 0.036%

    No Known Activations