© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143070
    Prev
    Next
    INDEX
    Explanations

    running or finding evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    谍
    0.45
    સ્પ
    0.44
    eszcze
    0.44
    ếp
    0.43
    AC
    0.42
     hiểu
    0.42
    ivi
    0.42
    嗖
    0.41
    近い
    0.41
    p
    0.41
    POSITIVE LOGITS
     fungsi
    0.48
     Sermon
    0.47
     insufficiency
    0.45
     functor
    0.45
     KNN
    0.44
     LSTM
    0.44
     OutputStream
    0.44
     grond
    0.43
     ഉറ
    0.43
     características
    0.43
    Activations Density 0.001%

    No Known Activations