© 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. 2157
    Prev
    Next
    INDEX
    Explanations

    being and doing

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

    exploring actively

    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
     anty
    0.22
     或
    0.21
     或者
    0.19
     þat
    0.19
     ordres
    0.19
    ل
    0.19
     jml
    0.18
    य
    0.18
    或者
    0.18
     blev
    0.18
    POSITIVE LOGITS
     trying
    0.33
     doing
    0.29
     preparing
    0.27
    trying
    0.26
     discussing
    0.25
     talking
    0.25
     actively
    0.25
     struggling
    0.25
     frantically
    0.24
     making
    0.24
    Activations Density 0.824%

    No Known Activations