© 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-262K
    7. 45315
    Prev
    Next
    INDEX
    Explanations

    . and abbreviations

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

    manufacturing inquiry, customization, writing

    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_262k_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
     $(`.
    0.48
    expandedTitle
    0.45
    计数
    0.44
     HSPB
    0.44
     isEqual
    0.43
    mixer
    0.43
     ريد
    0.43
     子供
    0.42
    较低
    0.42
    醎
    0.42
    POSITIVE LOGITS
    .
    0.54
    como
    0.48
    ﺤ
    0.47
    iv
    0.47
    il
    0.46
     como
    0.46
    i
    0.46
    Iv
    0.45
    uncu
    0.45
    ight
    0.45
    Activations Density 0.001%

    No Known Activations