© 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. 6828
    Prev
    Next
    INDEX
    Explanations

    on the telephone

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

    depends on conditions

    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
    阏
    0.45
    ফান
    0.43
    刑
    0.42
    squared
    0.41
    オリジナル
    0.41
     цієї
    0.41
    fficacy
    0.41
    🏽
    0.40
    ッセ
    0.40
     této
    0.39
    POSITIVE LOGITS
     startled
    0.48
     telepon
    0.48
     telefone
    0.47
     heo
    0.45
     mutable
    0.44
     telephone
    0.44
     cellphone
    0.44
     mobili
    0.44
     전화
    0.44
     বৈদেশিক
    0.43
    Activations Density 0.000%

    No Known Activations