© 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. 70430
    Prev
    Next
    INDEX
    Explanations

    inf

    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
    '
    -2.39
     včetně
    -2.08
     FROM
    -1.92
     включая
    -1.92
     ساعد
    -1.90
    ,))
    -1.89
     dritten
    -1.86
    つづく
    -1.77
    рим
    -1.76
    Naturally
    -1.76
    POSITIVE LOGITS
    s
    3.72
    ]
    2.44
    л
    2.41
    _
    2.31
    “
    2.17
    ים
    2.16
    н
    2.09
    ress
    2.05
     едва
    2.03
    踅
    1.94
    Activations Density 0.004%

    No Known Activations