© 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. 111438
    Prev
    Next
    INDEX
    Explanations

    "from that"

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

    combinations, rain, information, impact, stones, samples

    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
     الن
    0.48
     П
    0.47
     ไม่มี
    0.47
     น
    0.47
     Сте
    0.46
     الل
    0.46
     आदेश
    0.45
    𝗛
    0.45
     التد
    0.45
     سنة
    0.45
    POSITIVE LOGITS
    and
    0.52
    南方
    0.46
    illage
    0.43
    ">,</
    0.40
    và
    0.40
    ,]$
    0.40
    with
    0.40
     parishioners
    0.40
    icating
    0.39
    fected
    0.39
    Activations Density 0.000%

    No Known Activations