© 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. 49254
    Prev
    Next
    INDEX
    Explanations

    foreign and code tokens

    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
     canela
    -0.87
     Janssen
    -0.86
     témoignage
    -0.82
    初
    -0.79
    ->___
    -0.78
    Cape
    -0.78
     confirma
    -0.77
     Indications
    -0.77
    ="#
    -0.76
     Confirm
    -0.76
    POSITIVE LOGITS
     theme
    1.02
     Blätter
    0.88
    sera
    0.81
     fournisse
    0.81
     ダブル
    0.80
     тему
    0.78
    Abbiamo
    0.76
    VERT
    0.75
    Siamo
    0.74
    cielo
    0.74
    Activations Density 0.004%

    No Known Activations