© 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. 150986
    Prev
    Next
    INDEX
    Explanations

    desire for outcome

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

    frequency, type, or dependency

    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
    Url
    0.50
    t
    0.49
    aing
    0.48
    你能
    0.46
    h
    0.45
    评论
    0.45
    잊
    0.44
    商人
    0.44
    c
    0.43
    p
    0.43
    POSITIVE LOGITS
     optimality
    0.51
    ទាំង
    0.49
     creciente
    0.49
     समानता
    0.48
     თვით
    0.47
    ராய
    0.44
    rospection
    0.44
     proximal
    0.43
     synchronization
    0.43
     conformity
    0.43
    Activations Density 0.001%

    No Known Activations