© 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. 1455
    Prev
    Next
    INDEX
    Explanations

    person told

    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
    SAY
    -1.13
    Saying
    -1.13
    say
    -0.99
    mentions
    -0.97
     Saying
    -0.91
     الإنسان
    -0.91
    Say
    -0.90
    saying
    -0.90
    suggest
    -0.84
     kuwa
    -0.83
    POSITIVE LOGITS
     told
    5.84
    told
    3.50
     Told
    3.23
    Told
    2.56
     tell
    2.30
     tells
    2.28
    告诉
    2.23
     telling
    2.16
     Tell
    1.90
    告訴
    1.71
    Activations Density 0.050%

    No Known Activations