© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71053
    Prev
    Next
    INDEX
    Explanations

    million billion dollar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ストライプ
    -2.22
     certaines
    -2.09
    尨
    -2.06
     フリル
    -2.03
     theses
    -1.98
    ◨
    -1.98
     quando
    -1.94
    aian
    -1.93
     kleines
    -1.91
     刺繍
    -1.91
    POSITIVE LOGITS
    "
    2.58
    s
    2.36
    le
    2.23
     "
    2.22
    ،
    2.02
    <0xE1>
    1.95
    $
    1.95
    镒
    1.95
    {
    1.91
     viable
    1.90
    Activations Density 0.016%

    No Known Activations