© 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. 34-GEMMASCOPE-RES-131K
    7. 30458
    Prev
    Next
    INDEX
    Explanations

    verbs indicating intent or desire

    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_34/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
    alties
    -1.18
    haviours
    -1.11
     numberOf
    -1.05
     these
    -1.03
     barata
    -0.99
    ονται
    -0.98
    ються
    -0.97
    ídas
    -0.97
     cruzado
    -0.97
     flesta
    -0.96
    POSITIVE LOGITS
     to
    1.66
    得
    1.44
     لإ
    0.98
     dependiendo
    0.94
    well
    0.93
    C
    0.91
    But
    0.91
    q
    0.90
     reg
    0.90
    <b>
    0.88
    Activations Density 0.006%

    No Known Activations