© 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. 10-GEMMASCOPE-RES-131K
    7. 29185
    Prev
    Next
    INDEX
    Explanations

    rental items and services

    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_10/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
    '
    -2.58
    s
    -2.47
    v
    -2.08
    u
    -1.99
    ]
    -1.95
            
    -1.92
    }{
    -1.92
     {
    -1.91
    ang
    -1.84
    猻
    -1.84
    POSITIVE LOGITS
    逦
    2.09
    ⬈
    2.08
     inspiré
    2.02
     TAMBIÉN
    1.99
     basé
    1.98
     basée
    1.91
    퐹
    1.88
     ktore
    1.88
     fabriqué
    1.87
    OLPH
    1.87
    Activations Density 0.009%

    No Known Activations