© 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. 16154
    Prev
    Next
    INDEX
    Explanations

    also followed by verbs

    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
    DebuggerNonUser
    -1.55
    corrhi
    -1.49
    感じです
    -1.48
     and
    -1.48
    AddTagHelper
    -1.45
    ようで
    -1.44
    complexContent
    -1.43
    久し
    -1.41
     eerste
    -1.41
     laiton
    -1.40
    POSITIVE LOGITS
    が
    1.83
    は
    1.82
    ,
    1.79
    a
    1.66
     also
    1.62
    i
    1.52
     Grüßen
    1.49
     has
    1.48
     is
    1.48
    与此同时
    1.47
    Activations Density 0.042%

    No Known Activations