© 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. 49403
    Prev
    Next
    INDEX
    Explanations

    android resource paths

    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
     św
    -0.84
     pows
    -0.82
     vort
    -0.79
     capability
    -0.78
    AZINE
    -0.77
     goma
    -0.77
     negotiation
    -0.75
     susten
    -0.74
    GetKeyDown
    -0.74
     potes
    -0.73
    POSITIVE LOGITS
     android
    1.09
    android
    0.89
     še
    0.85
    schemas
    0.81
    Finanz
    0.77
     Дмитрий
    0.77
    طرز
    0.76
    otone
    0.76
    бие
    0.75
    良かったです
    0.72
    Activations Density 0.048%

    No Known Activations