© 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. 65723
    Prev
    Next
    INDEX
    Explanations

    elaboration or specification

    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
    栳
    -1.34
    这些
    -1.16
     Diese
    -1.12
    discovered
    -1.12
     esses
    -1.11
     suav
    -1.09
    vább
    -1.08
    訫
    -1.08
     этих
    -1.04
    estos
    -1.04
    POSITIVE LOGITS
     example
    1.59
     accordingly
    1.58
     например
    1.56
     therefore
    1.53
     especially
    1.52
     examples
    1.48
     particularly
    1.43
     specifically
    1.42
    例えば
    1.38
     include
    1.33
    Activations Density 0.038%

    No Known Activations