© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 39
    Prev
    Next
    INDEX
    Explanations

    symbols followed by text

    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_16_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
    ،
    0.64
     that
    0.55
    ।
    0.55
    }
    0.52
    ។
    0.47
     a
    0.47
    {
    0.46
     aneur
    0.45
     échanc
    0.45
    "
    0.44
    POSITIVE LOGITS
    ay
    0.48
    op
    0.45
    Y
    0.43
    ছে
    0.43
    其他
    0.42
    is
    0.41
    ان
    0.40
    出
    0.40
    ка
    0.40
    ل
    0.40
    Activations Density 2.825%

    No Known Activations