© 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. 107614
    Prev
    Next
    INDEX
    Explanations

    reason or lack of reason

    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
    𝘁
    -0.82
    짱
    -0.80
    desired
    -0.79
    тах
    -0.79
    beitet
    -0.78
     possibilità
    -0.77
    erenc
    -0.77
     BEAUTIFUL
    -0.75
     actes
    -0.75
    }}=\
    -0.74
    POSITIVE LOGITS
     good
    2.92
     compelling
    2.81
     reason
    2.81
     reasons
    2.80
     valid
    2.50
    reasons
    2.13
     Reasons
    2.13
     razones
    1.91
    Reasons
    1.89
     justification
    1.88
    Activations Density 0.046%

    No Known Activations