© 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. 48744
    Prev
    Next
    INDEX
    Explanations

    maximum integer values

    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
     aware
    -0.88
     موا
    -0.83
     jūsų
    -0.78
    ecal
    -0.77
     noticed
    -0.77
     īpa
    -0.77
    にん
    -0.75
    介意
    -0.74
     mūsų
    -0.73
     adamant
    -0.73
    POSITIVE LOGITS
     value
    1.30
    value
    1.16
     valeur
    1.11
     VALUE
    1.02
    VALUE
    0.96
    値
    0.93
     AUSSI
    0.91
     ilgi
    0.89
    uchos
    0.87
    mum
    0.85
    Activations Density 0.004%

    No Known Activations