Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8865
    Prev
    Next
    INDEX
    Explanations

    terms of address for people

    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
     guys
    -1.75
     and
    -1.63
     dude
    -1.59
     guy
    -1.38
     to
    -1.37
     sir
    -1.37
     or
    -1.27
     sweetie
    -1.27
     for
    -1.21
     dear
    -1.19
    POSITIVE LOGITS
     certains
    1.07
    ctrica
    1.06
    ógio
    1.05
     revelou
    1.05
     exercer
    1.05
     gardent
    1.02
    hers
    1.02
     relatif
    1.01
     alarme
    1.00
     rocha
    0.99
    Activations Density 0.019%

    No Known Activations