© 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. 76827
    Prev
    Next
    INDEX
    Explanations

    elicits information or responses

    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
     sends
    -0.84
    捡
    -0.80
     sending
    -0.79
    ὄ
    -0.75
     memberikan
    -0.75
     кур
    -0.75
    щать
    -0.74
     mutat
    -0.74
     ബ
    -0.74
    itim
    -0.71
    POSITIVE LOGITS
     elic
    3.42
     elicit
    3.39
     elicited
    3.19
     coax
    2.31
     extracting
    2.17
     extract
    2.16
     extracted
    1.83
     soliciting
    1.80
    extract
    1.80
     evoke
    1.70
    Activations Density 0.073%

    No Known Activations