© 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. 152082
    Prev
    Next
    INDEX
    Explanations

    your CV and information

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

    extracting information or details

    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
     покажу
    0.50
    橑
    0.49
    阊
    0.48
    ходе
    0.47
     разру
    0.47
     появления
    0.47
     другая
    0.46
     клавиа
    0.46
     एंट्रेंस
    0.46
     केमिस्ट्री
    0.45
    POSITIVE LOGITS
    OW
    0.56
     vyt
    0.51
    ITIS
    0.50
     orthodoxy
    0.46
     inqui
    0.45
     ਸਮ
    0.45
     réalis
    0.44
     ገ
    0.44
    Conta
    0.44
    AndUpdate
    0.43
    Activations Density 0.000%

    No Known Activations