© 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. 14011
    Prev
    Next
    INDEX
    Explanations

    Serpent, digits, Tet Offensive

    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
    ker
    2.18
    gan
    2.02
    kent
    1.99
    wärts
    1.92
    дан
    1.91
    滉
    1.88
    ahanglan
    1.85
    тири
    1.83
    king
    1.81
    kan
    1.76
    POSITIVE LOGITS
    निश्ड
    2.48
    FY
    2.46
    eber
    2.40
     época
    2.27
     showAlert
    2.20
    कॉइन
    2.16
    replaceAll
    2.15
     programación
    2.15
    自
    2.13
    ifferentiate
    2.12
    Activations Density 0.038%

    No Known Activations