© 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. 97570
    Prev
    Next
    INDEX
    Explanations

    compared to average

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

    Okay, excellent!

    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
    rightarrow
    0.47
     пові
    0.44
     pourra
    0.43
    ๛
    0.43
    荪
    0.43
     Fluss
    0.42
     professeur
    0.40
     ভারতীয়রা
    0.40
     bereits
    0.40
     problèmes
    0.40
    POSITIVE LOGITS
     of
    0.55
    of
    0.48
     is
    0.47
     بشكل
    0.46
     &
    0.44
     necessitates
    0.44
     droga
    0.44
     ਅਤੇ
    0.44
     and
    0.43
     এবং
    0.42
    Activations Density 0.001%

    No Known Activations