© 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. 22-GEMMASCOPE-RES-131K
    4. 13188
    Prev
    Next
    INDEX
    Explanations

    identifier, version, code

    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_22/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
     algas
    -1.09
     vokal
    -1.08
    miert
    -1.01
    secon
    -1.01
    Matin
    -1.00
    𝘒
    -0.99
     embri
    -0.97
     ovale
    -0.96
     akrab
    -0.96
    Área
    -0.96
    POSITIVE LOGITS
    Пі
    1.18
     суток
    0.98
    }
    
    
    0.98
     descriptive
    0.98
    പ
    0.97
    atula
    0.96
    }
    0.96
     OGSÅ
    0.95
    зи
    0.94
    ungu
    0.94
    Activations Density 0.002%

    No Known Activations