© 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. 22-GEMMASCOPE-RES-131K
    7. 72861
    Prev
    Next
    INDEX
    Explanations

    "."

    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_22/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
    :
    -2.52
     is
    -2.03
     sooooo
    -1.99
     What
    -1.90
     observar
    -1.88
     foram
    -1.82
    涐
    -1.81
     If
    -1.79
     otorga
    -1.77
    _{
    -1.76
    POSITIVE LOGITS
    羕
    2.53
    re
    2.47
    2
    2.39
    ーーー
    2.27
     haupts
    2.25
    Y
    2.17
     zweifel
    2.11
     verkau
    2.08
    1
    2.08
    ほんと
    2.02
    Activations Density 0.011%

    No Known Activations