© 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. 119511
    Prev
    Next
    INDEX
    Explanations

    kim kardashian, smart points

    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
    }
    -2.19
    8
    -1.91
    )
    -1.83
    mathrm
    -1.80
    5
    -1.72
    你不
    -1.67
    6
    -1.67
    1
    -1.58
    7
    -1.55
    ]
    -1.50
    POSITIVE LOGITS
     to
    2.52
     a
    1.94
     and
    1.80
     where
    1.72
     for
    1.71
     from
    1.64
     of
    1.63
     based
    1.60
    鹛
    1.58
     when
    1.55
    Activations Density 0.044%

    No Known Activations