© 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. 1215
    Prev
    Next
    INDEX
    Explanations

    percentages and counts

    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
    ings
    2.08
    light
    2.01
    esse
    1.90
    way
    1.84
    ge
    1.81
    wind
    1.77
    াম
    1.74
    h
    1.70
    ne
    1.58
     bear
    1.58
    POSITIVE LOGITS
    клады
    1.92
    蒻
    1.88
    র্ক
    1.87
    xception
    1.86
    ધું
    1.85
    ረጥ
    1.84
    ့်
    1.84
     голова
    1.82
    roskop
    1.82
    myfaces
    1.81
    Activations Density 0.643%

    No Known Activations