© 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. 187952
    Prev
    Next
    INDEX
    Explanations

    first in a series

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

    lost in

    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
     chand
    0.49
    нього
    0.46
     eisen
    0.41
     allegiance
    0.41
    }]\
    0.41
    })}{\
    0.40
    喟
    0.40
    SIAN
    0.40
     auto
    0.39
    ener
    0.39
    POSITIVE LOGITS
     a
    0.57
    a
    0.53
     جدید
    0.52
     μια
    0.51
     the
    0.49
     sebuah
    0.49
     ভবিষ্যতে
    0.48
    একটি
    0.48
     Utama
    0.48
     München
    0.47
    Activations Density 0.002%

    No Known Activations