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. 110101
    Prev
    Next
    INDEX
    Explanations

    interfaith dialogue and tolerance

    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
     turquesa
    -0.88
     bible
    -0.85
    Kelly
    -0.85
    存于互联网档案馆
    -0.84
    ᱵ
    -0.82
    🦜
    -0.82
     rebellion
    -0.81
     asexual
    -0.81
    🚤
    -0.79
     feral
    -0.79
    POSITIVE LOGITS
     dialogue
    1.88
     dialog
    1.70
     dialogo
    1.62
     Dialogue
    1.59
    Dialogue
    1.46
     Dialog
    1.45
    dialogue
    1.41
     diálogo
    1.38
     DIALOG
    1.34
     tolerance
    1.32
    Activations Density 0.025%

    No Known Activations