© 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. 112609
    Prev
    Next
    INDEX
    Explanations

    words indicating state or possibility

    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
     selben
    -1.56
     It
    -1.55
     Meanwhile
    -1.45
    不是
    -1.44
    <bos>
    -1.43
     gleichen
    -1.42
     Specifically
    -1.42
     Würde
    -1.38
    感じた
    -1.36
     Likewise
    -1.35
    POSITIVE LOGITS
     of
    1.41
    nyard
    1.37
    錞
    1.35
    :'#
    1.33
    new
    1.31
    zeniami
    1.31
    ⤞
    1.29
     lakini
    1.29
     ahora
    1.28
    Vaya
    1.27
    Activations Density 0.007%

    No Known Activations