© 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. 26473
    Prev
    Next
    INDEX
    Explanations

    is a / was a

    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
     ):
    -1.03
    ：“……”
    -1.01
     to
    -0.96
    сі
    -0.95
    elsif
    -0.92
    ating
    -0.88
    providedIn
    -0.85
     taal
    -0.85
    Rate
    -0.85
    </i>
    -0.85
    POSITIVE LOGITS
    馳
    0.98
    ῖς
    0.96
     defStyle
    0.92
    rinth
    0.91
     makeshift
    0.90
     mergeFrom
    0.90
     moléculas
    0.90
    oredCriteria
    0.89
     if
    0.88
    avits
    0.88
    Activations Density 0.646%

    No Known Activations