© 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. 16111
    Prev
    Next
    INDEX
    Explanations

    Android operating system versions

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

    Android operating system software

    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
    读取
    0.54
     读取
    0.48
    蒾
    0.47
    用来
    0.47
    🗡
    0.46
    👓
    0.45
    ಗು
    0.44
     やつ
    0.44
    כ
    0.44
    非法
    0.44
    POSITIVE LOGITS
     Software
    0.45
     stalwart
    0.45
     sheen
    0.45
     adaptation
    0.44
    Software
    0.44
     delivery
    0.42
     Lite
    0.42
     suitability
    0.42
     Performance
    0.41
     Adaptation
    0.41
    Activations Density 0.027%

    No Known Activations