© 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. 173344
    Prev
    Next
    INDEX
    Explanations

    we are, thermal mass, more compact

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

    tour itineraries

    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
    dataReader
    0.49
    结果
    0.47
    罚
    0.45
    पों
    0.44
     আক্রম
    0.44
     ô
    0.44
    يدات
    0.44
     μεγά
    0.43
    冢
    0.43
    castle
    0.42
    POSITIVE LOGITS
     hry
    0.54
     स
    0.48
     snacks
    0.46
     tick
    0.46
    আলো
    0.45
     holidays
    0.44
    म
    0.44
     budete
    0.44
     शाम
    0.44
     disabilities
    0.43
    Activations Density 0.001%

    No Known Activations