© 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. 247691
    Prev
    Next
    INDEX
    Explanations

    code and formats

    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
    小
    0.54
    아
    0.52
     прия
    0.51
    лку
    0.51
    Ра
    0.50
     інші
    0.50
     小
    0.49
     Анти
    0.49
     有限
    0.48
    <code>
    0.48
    POSITIVE LOGITS
    عدد
    0.47
    rents
    0.46
    }></
    0.45
    <unused88>
    0.45
    }})\
    0.44
     vær
    0.43
    भरा
    0.42
     dosa
    0.42
     births
    0.42
     meghatá
    0.42
    Activations Density 0.001%

    No Known Activations