© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65829
    Prev
    Next
    INDEX
    Explanations

    morally objectionable or hateful speech

    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
     åren
    -1.08
    tió
    -1.05
     possibilité
    -1.02
    тельства
    -1.00
     SITY
    -0.98
     možnosti
    -0.97
    ㍑
    -0.96
    ateľ
    -0.95
     illusions
    -0.94
     multicolore
    -0.94
    POSITIVE LOGITS
     a
    2.52
     an
    1.77
     akin
    1.57
     equivalent
    1.21
    是一种
    1.20
     putting
    1.15
    การ
    1.13
     evidence
    1.09
     taking
    1.02
     called
    1.01
    Activations Density 0.055%

    No Known Activations