© 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. 66275
    Prev
    Next
    INDEX
    Explanations

    each otherderived fromhave received

    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
    jarah
    -0.84
     superare
    -0.83
     pues
    -0.79
    tamentos
    -0.78
    メント
    -0.73
    
    -0.73
     APC
    -0.72
     zatrzy
    -0.71
    žad
    -0.71
    فضل
    -0.71
    POSITIVE LOGITS
     Danube
    0.77
     donna
    0.76
    Qualifier
    0.75
     pof
    0.75
    🦂
    0.73
    tried
    0.73
     syndicate
    0.72
    Ejec
    0.72
    Robot
    0.71
     Debe
    0.71
    Activations Density 0.004%

    No Known Activations