© 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. 26231
    Prev
    Next
    INDEX
    Explanations

    or and

    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
    いずれ
    -1.05
     here
    -0.98
    glBindBuffer
    -0.97
     such
    -0.94
     autonomia
    -0.91
    眼里
    -0.91
    についても
    -0.91
    どれも
    -0.89
     Dě
    -0.89
     successor
    -0.85
    POSITIVE LOGITS
     or
    1.26
     and
    1.15
    Größe
    1.01
    UIP
    0.97
    ého
    0.90
     Primarily
    0.85
     elseif
    0.84
    staden
    0.84
    apimachinery
    0.82
    lanmış
    0.82
    Activations Density 0.051%

    No Known Activations