© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75413
    Prev
    Next
    INDEX
    Explanations

    following / last / this

    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
     premise
    -0.82
    Premise
    -0.78
     concepto
    -0.78
    autogui
    -0.78
     بق
    -0.76
     Theorem
    -0.76
    }*/
    -0.75
    र्जा
    -0.74
    上前
    -0.74
     subset
    -0.74
    POSITIVE LOGITS
     equality
    1.09
     last
    1.06
    last
    0.98
     равен
    0.98
    Last
    0.96
     displayed
    0.95
    LAST
    0.95
     statements
    0.88
    ẳng
    0.87
     последний
    0.86
    Activations Density 0.046%

    No Known Activations