© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 245293
    Prev
    Next
    INDEX
    Explanations

    android attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ौ
    0.50
    Substituting
    0.49
    രീക്ഷ
    0.49
    ران
    0.47
    杣
    0.46
    จ
    0.43
    เคย
    0.43
    到的
    0.42
    ন
    0.42
    毖
    0.42
    POSITIVE LOGITS
     android
    0.47
    android
    0.45
     সম্ভবত
    0.45
    terminated
    0.44
     resultContent
    0.44
     attributes
    0.43
     Android
    0.43
     attribute
    0.42
     ContentValues
    0.42
    value
    0.42
    Activations Density 0.000%

    No Known Activations