© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40258
    Prev
    Next
    INDEX
    Explanations

    Sak, Sakari, Sakamoto, Sakhalin, Sakai

    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
    there
    -3.08
    
    -2.94
    ),
    -2.84
     sorgt
    -2.39
     gustado
    -2.31
    ୌ
    -2.30
    サイズは
    -2.27
    días
    -2.25
    If
    -2.19
     vague
    -2.17
    POSITIVE LOGITS
    vège
    2.78
     刺繍
    2.63
    __':
    2.56
    瘣
    2.48
    羕
    2.45
    which
    2.44
    2
    2.44
     exitosa
    2.42
    詢問
    2.41
     celebrid
    2.38
    Activations Density 0.002%

    No Known Activations