© 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. 31562
    Prev
    Next
    INDEX
    Explanations

    its way

    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
    Zutaten
    -0.99
    Funktion
    -0.86
    ት
    -0.81
     opportunities
    -0.81
     msk
    -0.80
     purpure
    -0.80
    itats
    -0.79
     taka
    -0.79
     boucle
    -0.78
    ⃘
    -0.78
    POSITIVE LOGITS
     way
    1.01
    得好
    0.81
     जब
    0.79
     sombre
    0.78
     بالإضافة
    0.76
     relacionados
    0.75
     ženy
    0.74
     was
    0.74
     Wel
    0.73
     Melanie
    0.73
    Activations Density 0.016%

    No Known Activations