© 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. 14021
    Prev
    Next
    INDEX
    Explanations

    just ask

    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
    ีด
    2.75
    ứ
    2.48
    থেষ্ট
    2.48
    πων
    2.46
    abeled
    2.44
    }_{(
    2.43
    quinho
    2.40
    ඡ
    2.39
    handles
    2.39
    ্দ্র
    2.34
    POSITIVE LOGITS
    тации
    2.87
    inare
    2.68
     Frem
    2.60
    𝙧
    2.58
    ramid
    2.55
    లీ
    2.52
    lications
    2.46
    бліоте
    2.46
    स्वर
    2.46
    toff
    2.43
    Activations Density 0.018%

    No Known Activations