© 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. 99175
    Prev
    Next
    INDEX
    Explanations

    android sdk android studio

    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
     Baghdad
    -0.80
    TouchListener
    -0.77
    SCL
    -0.76
     busted
    -0.74
     Rye
    -0.74
    thene
    -0.73
     NotImplemented
    -0.72
    骶
    -0.71
     Ши
    -0.71
    backdrop
    -0.70
    POSITIVE LOGITS
    android
    0.91
     Android
    0.88
     android
    0.83
    Android
    0.82
     STUDIO
    0.74
     Blackman
    0.74
    STUDIO
    0.73
    studio
    0.72
    Nexus
    0.72
    Google
    0.71
    Activations Density 0.183%

    No Known Activations