© 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. 104178
    Prev
    Next
    INDEX
    Explanations

    Karen followed by surname

    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
     Einzelnen
    -2.69
     were
    -2.38
    örté
    -2.34
     материалы
    -2.31
    点的
    -2.30
    “
    -2.28
    o
    -2.28
    鬟
    -2.23
    ????
    -2.22
    ]
    -2.20
    POSITIVE LOGITS
    鉝
    2.53
    ଃ
    2.36
    );
    2.36
    
    2.34
     案例
    2.33
    r
    2.31
    广大
    2.25
    na
    2.25
    裢
    2.25
    ↀ
    2.20
    Activations Density 0.009%

    No Known Activations