© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11639
    Prev
    Next
    INDEX
    Explanations

    defining what something is

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

    define what's next

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

    define

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_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
     estimations
    0.64
    ፫
    0.64
     megjelen
    0.62
     }.
    0.61
     audits
    0.61
     glimpses
    0.61
     Bolts
    0.61
     activations
    0.60
     commemorate
    0.60
    磡
    0.59
    POSITIVE LOGITS
    定義
    1.08
     정의
    0.93
    defined
    0.89
    Defined
    0.89
     Defining
    0.87
    as
    0.86
     defining
    0.85
    Defining
    0.85
     Defines
    0.84
     definisi
    0.84
    Activations Density 0.109%

    No Known Activations