© 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. 107578
    Prev
    Next
    INDEX
    Explanations

    author, Chan, Home, Pear, Cob

    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
    assem
    -0.79
    tob
    -0.79
     GreatSchools
    -0.77
    awin
    -0.74
     gelegen
    -0.71
     arrivant
    -0.71
    STI
    -0.71
     pastas
    -0.70
     Jacks
    -0.70
    Analyst
    -0.69
    POSITIVE LOGITS
     Death
    0.78
    tega
    0.77
    Traditional
    0.76
    แฟน
    0.73
     DEATH
    0.73
     cozy
    0.73
    DEATH
    0.72
    鼻
    0.71
     Traditional
    0.71
     amateur
    0.70
    Activations Density 0.032%

    No Known Activations