© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72711
    Prev
    Next
    INDEX
    Explanations

    that/who followed by 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_22/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
     what
    -1.52
     verkoop
    -1.45
     and
    -1.44
     maakte
    -1.44
     kellett
    -1.41
     you
    -1.38
     tenido
    -1.37
     ziekte
    -1.34
    PENDAHULUAN
    -1.34
    際には
    -1.34
    POSITIVE LOGITS
    が
    1.51
    </em>
    1.40
     अपने
    1.36
    の
    1.31
    ですが
    1.29
         
    1.25
        
    1.23
    ఱ
    1.23
    薔薇
    1.21
    は
    1.21
    Activations Density 0.066%

    No Known Activations