© 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. 8663
    Prev
    Next
    INDEX
    Explanations

    stands for or in a location

    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
    ⡪
    -3.25
    鯪
    -3.11
    
    -2.83
    ſam
    -2.63
    鳢
    -2.58
    ᭝
    -2.55
    ꪔ
    -2.53
     für
    -2.50
     декабря
    -2.48
    deckung
    -2.47
    POSITIVE LOGITS
     
    5.16
    '
    3.55
    "
    2.69
     We
    2.52
    selbe
    2.41
    此外
    2.41
    独特
    2.33
    除此之外
    2.28
    以外
    2.28
     —
    2.28
    Activations Density 0.009%

    No Known Activations