© 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. 14010
    Prev
    Next
    INDEX
    Explanations

    ADHD discussions

    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
    e
    2.13
    z
    2.06
    is
    2.02
    je
    2.01
    i
    1.87
    هي
    1.78
     z
    1.74
    ov
    1.72
    enz
    1.69
    ion
    1.64
    POSITIVE LOGITS
    トラック
    2.73
     Интернет
    2.72
    粞
    2.65
    มาะ
    2.60
     Espíritu
    2.60
    棌
    2.59
    䐝
    2.56
    𒇽
    2.55
    昷
    2.53
    𒊍
    2.53
    Activations Density 0.002%

    No Known Activations