© 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. 34-GEMMASCOPE-RES-131K
    7. 1163
    Prev
    Next
    INDEX
    Explanations

    have / has / had occurrences

    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
     gehabt
    -1.15
    HAD
    -1.13
    Had
    -1.11
     Offers
    -1.06
     HAVING
    -1.04
    HAV
    -0.95
    Got
    -0.94
    Provide
    -0.94
     Having
    -0.94
    HAS
    -0.94
    POSITIVE LOGITS
     have
    2.05
     has
    1.52
     نے
    1.34
     đã
    1.22
     abbiamo
    1.20
     telah
    1.19
     उन्होंने
    0.97
    watts
    0.85
     Doria
    0.84
     pengusaha
    0.83
    Activations Density 0.110%

    No Known Activations