© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84490
    Prev
    Next
    INDEX
    Explanations

    verbs of wanting and knowing

    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
     will
    -1.66
     which
    -1.52
     When
    -1.47
     also
    -1.42
     where
    -1.38
     because
    -1.36
    ).
    -1.34
     bedeutet
    -1.34
     asegurarse
    -1.32
    )'
    -1.30
    POSITIVE LOGITS
    慫
    1.34
    ჻
    1.34
     respective
    1.31
    ,
    1.22
    ;
    
    1.20
    粜
    1.20
    èles
    1.20
     neste
    1.17
    が欲しい
    1.16
    both
    1.15
    Activations Density 0.083%

    No Known Activations