© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12598
    Prev
    Next
    INDEX
    Explanations

    4 followed by numbers or punctuation

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

    rounding to 4 decimal places

    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
    يد
    0.82
    시
    0.80
    ور
    0.80
    ви
    0.77
    AssetDiscovery
    0.76
    ור
    0.73
    ﭑ
    0.72
     nhiên
    0.70
    kiego
    0.70
    <unused2125>
    0.70
    POSITIVE LOGITS
    ش
    1.00
    4
    0.90
    :
    0.87
    <0x0D>
    0.84
    2
    0.81
    ;
    0.79
    し
    0.77
    n
    0.76
    ن
    0.75
     substitu
    0.75
    Activations Density 0.713%

    No Known Activations