© 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. 13926
    Prev
    Next
    INDEX
    Explanations

    activity durations in minutes

    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
    Scar
    1.52
     force
    1.52
    revision
    1.51
    force
    1.47
    ю
    1.46
    ҳ
    1.44
    play
    1.42
    endor
    1.41
    neu
    1.39
    с
    1.38
    POSITIVE LOGITS
     rinsing
    2.29
     purification
    2.00
    クロマト
    1.83
    濾
    1.83
    溶液
    1.82
     purifying
    1.82
     elution
    1.79
     chromatography
    1.79
     cairan
    1.78
     HPLC
    1.71
    Activations Density 0.208%

    No Known Activations