© 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. 30507
    Prev
    Next
    INDEX
    Explanations

    states following verb "to have"

    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
    fand
    -1.14
    terra
    -1.13
    ølge
    -1.12
    vatten
    -1.08
    &,
    -1.02
     carbone
    -1.00
    慘
    -1.00
     possuem
    -0.99
    ³,
    -0.98
    väl
    -0.97
    POSITIVE LOGITS
     been
    3.17
     not
    1.91
     had
    1.74
     recently
    1.60
     become
    1.59
     a
    1.46
     received
    1.40
     lost
    1.35
     never
    1.34
     no
    1.26
    Activations Density 0.070%

    No Known Activations