© 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. 203838
    Prev
    Next
    INDEX
    Explanations

    awakening, long, painting, churches, not

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

    technical terms and foreign scripts

    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
    座位
    0.44
    സ്തു
    0.41
     oreille
    0.41
    た
    0.41
     الانت
    0.40
     lectus
    0.40
    ス
    0.40
    輸入
    0.40
    زال
    0.39
    Seats
    0.39
    POSITIVE LOGITS
    adá
    0.42
     থেমে
    0.41
     Quốc
    0.40
     исход
    0.40
     Juz
    0.39
    ätt
    0.39
    OfWeek
    0.39
     প্রতিদিনই
    0.38
     Logout
    0.38
    éph
    0.38
    Activations Density 0.000%

    No Known Activations