© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15661
    Prev
    Next
    INDEX
    Explanations

    numbered lists and symbols

    np_acts-logits-general · gemini-2.5-flash-lite

    structured lists with bullet points and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
    ："
    0.44
     Slovenian
    0.41
     thwarted
    0.40
    फ्ट
    0.40
    ：（
    0.40
    ॉप
    0.39
    ፦
    0.39
     codef
    0.39
     алуу
    0.38
     İran
    0.38
    POSITIVE LOGITS
     AMAZING
    0.47
    !)
    0.46
    cmt
    0.46
     amazing
    0.45
    calories
    0.44
    ace
    0.43
    cin
    0.43
    mul
    0.43
    ugi
    0.43
    )
    0.43
    Activations Density 0.002%

    No Known Activations