© 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. 7735
    Prev
    Next
    INDEX
    Explanations

    mobile apps and operating systems

    np_acts-logits-general · gemini-2.5-flash-lite

    mobile apps and platforms

    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
     семина
    0.76
     cytokines
    0.65
     endot
    0.61
    IRCONIUM
    0.61
    Issledovatel
    0.60
     anhydride
    0.59
    CHREIB
    0.59
    腟
    0.57
    URNIZOR
    0.57
     antitumor
    0.56
    POSITIVE LOGITS
     Android
    1.96
    Android
    1.80
     iOS
    1.80
     android
    1.59
    iOS
    1.59
    android
    1.52
     iPhone
    1.41
     앱
    1.40
    安卓
    1.40
     apps
    1.39
    Activations Density 0.359%

    No Known Activations