© 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. 1057
    Prev
    Next
    INDEX
    Explanations

    AFC and Francesco 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
    </b>
    -3.36
    t
    -3.23
     «
    -3.19
    ]
    -2.83
     {
    -2.75
     unwavering
    -2.72
     burgeoning
    -2.66
    e
    -2.58
    f
    -2.56
    j
    -2.53
    POSITIVE LOGITS
    OUTUBE
    3.03
     accedi
    2.94
    驁
    2.84
    Ꮴ
    2.83
     concorda
    2.81
     alemão
    2.80
     assistente
    2.77
    沕
    2.72
     zijne
    2.72
    かもし
    2.70
    Activations Density 0.003%

    No Known Activations