© 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. 10-GEMMASCOPE-RES-131K
    4. 75367
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    昨
    -1.71
     riservata
    -1.63
     giapponese
    -1.57
     femminile
    -1.53
     penna
    -1.50
     tedesco
    -1.48
    ThemeOverlay
    -1.48
    łaś
    -1.47
     Caixa
    -1.46
     Vnd
    -1.44
    POSITIVE LOGITS
    却被
    1.66
    ],
    1.50
     "
    1.50
     ports
    1.41
     ,
    1.35
     port
    1.34
    ),
    1.33
    ]
    1.33
    art
    1.31
     the
    1.30
    Activations Density 0.075%

    No Known Activations