© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91716
    Prev
    Next
    INDEX
    Explanations

    constant / constants / Globals

    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
    æn
    -0.92
    だろ
    -0.87
     heard
    -0.84
     Fällen
    -0.82
    Kaynakça
    -0.81
    客人
    -0.81
    Teknik
    -0.78
     historii
    -0.78
     tuyệt
    -0.77
    engertian
    -0.77
    POSITIVE LOGITS
     Constant
    1.20
     constants
    1.16
     Constants
    1.11
     CONSTANT
    1.06
    constant
    1.03
    Constant
    1.02
    Constants
    1.00
    constants
    0.91
    viously
    0.90
    byes
    0.89
    Activations Density 0.007%

    No Known Activations