© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103566
    Prev
    Next
    INDEX
    Explanations

    what followed by pronoun/verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h3>
    -1.78
     $
    -1.77
     ")
    -1.64
     Он
    -1.60
     It
    -1.57
    攫
    -1.54
     know
    -1.54
    木材
    -1.51
     ")
    -1.48
     $\
    -1.45
    POSITIVE LOGITS
     素人
    1.59
     powied
    1.59
    ⩩
    1.59
     our
    1.53
     you
    1.48
    a
    1.48
    一会
    1.47
     wygod
    1.45
     humains
    1.43
    śmy
    1.42
    Activations Density 0.013%

    No Known Activations