© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102830
    Prev
    Next
    INDEX
    Explanations

    comment dates and "says"

    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
    seamnă
    -0.96
     огур
    -0.92
     romantis
    -0.88
     unang
    -0.86
    formatie
    -0.85
     alem
    -0.85
     samband
    -0.85
     minY
    -0.85
     Norge
    -0.83
     dakota
    -0.83
    POSITIVE LOGITS
     says
    1.45
     reply
    1.16
     said
    1.13
     Says
    1.06
     Reply
    0.98
    Reply
    0.95
     replies
    0.85
    says
    0.84
     October
    0.83
     on
    0.83
    Activations Density 0.017%

    No Known Activations