© 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. 3266
    Prev
    Next
    INDEX
    Explanations

    agreement and consent

    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
    ﮄ
    3.15
    Ƣ
    3.00
    मग
    2.74
    ખા
    2.68
     depository
    2.66
    ட்ரோ
    2.65
     Тя
    2.64
    ಖ
    2.63
     уен
    2.63
    Ꮯ
    2.62
    POSITIVE LOGITS
     সেক্রেটারি
    2.18
    den
    2.15
    ian
    2.14
    ष्णु
    2.05
    accio
    2.05
    he
    1.98
    yn
    1.87
    ourage
    1.86
    aye
    1.86
    agi
    1.86
    Activations Density 0.183%

    No Known Activations