© 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. 241603
    Prev
    Next
    INDEX
    Explanations

    accepted certain challenges

    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
    OG
    0.59
     ct
    0.54
     cong
    0.53
    0.50
     cc
    0.48
     cou
    0.47
    ONG
    0.46
     loc
    0.46
    \&
    0.46
    &
    0.45
    POSITIVE LOGITS
     χρώ
    0.54
     Ettha
    0.54
    airplane
    0.51
    ینا
    0.50
    ین
    0.50
    انگ
    0.49
    ناہ
    0.48
     ইহার
    0.48
    ቆዳ
    0.48
    敌人
    0.48
    Activations Density 0.000%

    No Known Activations