© 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. 15502
    Prev
    Next
    INDEX
    Explanations

    describing states or actions

    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
     this
    -1.11
    P
    -1.04
    ksesta
    -1.02
     G
    -1.01
    p
    -0.98
     P
    -0.98
    w
    -0.98
     D
    -0.97
     F
    -0.97
     S
    -0.96
    POSITIVE LOGITS
     also
    1.78
     também
    1.41
     asimismo
    1.32
     ciertamente
    1.29
     Também
    1.26
     téc
    1.20
     또
    1.20
     jedenfalls
    1.17
    fortnite
    1.17
    还会
    1.16
    Activations Density 0.025%

    No Known Activations