© 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. 236225
    Prev
    Next
    INDEX
    Explanations

    country frontiers

    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
     toot
    0.47
    ф
    0.47
    Create
    0.45
     і
    0.44
     нагре
    0.44
     openai
    0.44
    ک
    0.43
    Ма
    0.43
    хта
    0.43
    ፔ
    0.43
    POSITIVE LOGITS
    塡
    0.45
     Similarly
    0.43
     horas
    0.43
     時間
    0.43
    ຢ່າງ
    0.42
    marital
    0.42
     চাকরির
    0.42
     চাকরি
    0.42
    वहीं
    0.41
     उधर
    0.41
    Activations Density 0.000%

    No Known Activations