© 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. 11244
    Prev
    Next
    INDEX
    Explanations

    honey never spoils

    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
    a
    2.78
    i
    2.35
    aia
    2.29
    ️
    2.24
     .
    2.17
    يع
    2.11
    맴
    1.99
    an
    1.92
     fell
    1.91
    iato
    1.91
    POSITIVE LOGITS
    नी
    3.16
    ̗
    2.95
     secretNumber
    2.81
    é
    2.76
    ೋತಿ
    2.76
    幷
    2.75
    蕃
    2.70
    ValuePair
    2.70
    צל
    2.69
    নি
    2.69
    Activations Density 0.008%

    No Known Activations