© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11794
    Prev
    Next
    INDEX
    Explanations

    `const` declarations

    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
     that
    -1.86
     our
    -1.30
     such
    -1.30
     different
    -1.23
     any
    -1.19
     what
    -1.16
     was
    -1.15
     this
    -1.11
     Different
    -1.09
     will
    -1.05
    POSITIVE LOGITS
    const
    5.94
     const
    4.50
     the
    2.59
     Const
    2.38
    Const
    2.34
     CONST
    2.11
     constable
    1.88
     constante
    1.86
    CONST
    1.83
     constriction
    1.80
    Activations Density 0.046%

    No Known Activations