© 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. 30737
    Prev
    Next
    INDEX
    Explanations

    true, faithful, truer

    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
     burada
    -0.75
    zao
    -0.74
     violencia
    -0.74
    Mereka
    -0.74
    Ἐ
    -0.73
     سبيل
    -0.73
     wybór
    -0.73
     viņ
    -0.73
    Modelo
    -0.72
    午前
    -0.72
    POSITIVE LOGITS
     to
    1.56
     true
    1.25
    true
    0.99
     faithful
    0.94
    faithful
    0.83
     truer
    0.81
     True
    0.80
     👇
    0.80
     truest
    0.79
    SRP
    0.76
    Activations Density 0.027%

    No Known Activations