© 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. 71918
    Prev
    Next
    INDEX
    Explanations

    scroll bar

    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
     and
    -1.95
    い
    -1.92
    י
    -1.88
     但
    -1.82
     was
    -1.80
    Obviously
    -1.80
    i
    -1.78
    但他
    -1.74
    ться
    -1.73
     that
    -1.70
    POSITIVE LOGITS
    部分を
    2.16
     detención
    2.09
     przeznac
    2.02
    銛
    1.90
    にします
    1.86
     regain
    1.86
    鐿
    1.84
    z
    1.81
    凩
    1.78
    感慨
    1.77
    Activations Density 0.006%

    No Known Activations