© 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. 222984
    Prev
    Next
    INDEX
    Explanations

    sustainable profitable, French, holder, jointly

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

    code, project, tomography, brand, sensors

    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
    Если
    0.48
    พ
    0.47
    если
    0.47
     barcelona
    0.46
    Очень
    0.46
    וק
    0.45
     מג
    0.45
     menentukan
    0.44
     расту
    0.43
     negate
    0.43
    POSITIVE LOGITS
    ších
    0.53
    ý
    0.52
     sr
    0.50
    。,
    0.49
    لي
    0.49
    。(
    0.49
    urring
    0.47
    ្នក
    0.47
     أنه
    0.47
     કાર્યવાહી
    0.47
    Activations Density 0.001%

    No Known Activations