© 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. 53097
    Prev
    Next
    INDEX
    Explanations

    Sent from my iPhone

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

    mobile and smartphones

    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
    Sunflower
    0.44
     展示
    0.43
    getState
    0.42
    िकास
    0.42
     Sunflower
    0.41
     २०२
    0.40
    𝟐
    0.40
     УК
    0.39
     verwend
    0.39
     fach
    0.39
    POSITIVE LOGITS
     smartphone
    0.88
     mobile
    0.87
     iPhone
    0.82
    Mobile
    0.82
    スマホ
    0.81
    smartphone
    0.80
    mobile
    0.79
    iPhone
    0.77
    手机
    0.77
     mobiles
    0.77
    Activations Density 0.020%

    No Known Activations