© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5206
    Prev
    Next
    INDEX
    Explanations

    contrasting claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    гель
    1.42
    вање
    1.41
    Iter
    1.31
    ﺫ
    1.27
     Гор
    1.26
    дова
    1.21
     цикл
    1.21
    یاء
    1.20
     besteht
    1.19
     održ
    1.17
    POSITIVE LOGITS
     오히려
    2.19
     least
    2.02
     tampoco
    2.00
     anyhow
    1.97
    ぇ
    1.97
    oretically
    1.95
     prêts
    1.94
     그럼
    1.93
     anyway
    1.92
    むしろ
    1.91
    Activations Density 0.058%

    No Known Activations