© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12159
    Prev
    Next
    INDEX
    Explanations

    abstract nouns and qualities

    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
    Ҥ
    3.14
    ा
    3.09
    ље
    2.95
     balanceOf
    2.92
    𓏸
    2.92
    ीट
    2.91
    bibfnamefont
    2.89
    ﮄ
    2.88
    __(/*!
    2.88
    consulta
    2.86
    POSITIVE LOGITS
    hores
    3.02
    ჭ
    2.23
    ayers
    2.17
    ுங்கள்
    2.16
    agra
    2.13
     dint
    2.12
    hile
    2.11
    ha
    2.08
    অন্ত
    2.07
    ein
    2.06
    Activations Density 0.021%

    No Known Activations