© 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. 79146
    Prev
    Next
    INDEX
    Explanations

    patron saint or Latter-Day Saints

    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
    鳞
    -0.86
    Symbolic
    -0.83
    sword
    -0.82
     sexo
    -0.80
    symbolic
    -0.79
     SYMBOL
    -0.79
     SIGNAL
    -0.78
    soluble
    -0.76
    oke
    -0.76
     nitrogen
    -0.74
    POSITIVE LOGITS
     saints
    3.58
     saint
    3.36
     Saints
    3.17
     свя
    2.72
     holy
    2.61
     Saint
    2.59
     holiness
    2.59
    Saints
    2.56
    聖
    2.52
    Saint
    2.44
    Activations Density 0.033%

    No Known Activations