© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6374
    Prev
    Next
    INDEX
    Explanations

    Google DeepMind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    tinger
    1.67
     ameri
    1.50
    สุข
    1.46
    `);
    1.45
     उत्तराखण्ड
    1.44
     inquiring
    1.43
     Thurman
    1.43
     enqu
    1.42
    뵈
    1.39
    ด์
    1.38
    POSITIVE LOGITS
    явить
    0.98
     замо
    0.92
    Formula
    0.91
    вої
    0.91
    automne
    0.89
    ubro
    0.89
    력이
    0.89
     colère
    0.87
     міся
    0.85
     поддер
    0.85
    Activations Density 0.040%

    No Known Activations