© 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. 34-GEMMASCOPE-RES-131K
    7. 30365
    Prev
    Next
    INDEX
    Explanations

    boolean assignment or comparison

    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_34/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
     kirj
    -0.99
     accepter
    -0.91
    adalah
    -0.87
     logiciel
    -0.82
     Erwachsene
    -0.81
     Gibt
    -0.81
     isKindOfClass
    -0.81
     dégust
    -0.81
     decy
    -0.81
     goû
    -0.81
    POSITIVE LOGITS
     false
    1.53
     true
    1.30
     =
    1.28
     bool
    1.27
    false
    1.26
     boolean
    1.26
    =
    1.22
     untrue
    1.19
    bool
    1.17
     |=
    1.16
    Activations Density 0.003%

    No Known Activations