© 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. 61344
    Prev
    Next
    INDEX
    Explanations

    friend and friends

    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
     meestal
    -2.34
    </em>
    -2.28
    柺
    -2.27
    𓐍
    -2.19
    ↵
    -2.17
    </strong>
    -2.11
    一秒
    -2.00
    uitton
    -1.95
     tevens
    -1.94
    最多的
    -1.94
    POSITIVE LOGITS
     However
    2.38
     seperti
    2.30
     setelah
    2.27
    \
    2.27
    A
    2.16
     LIKE
    2.08
     في
    2.02
     universitaire
    1.98
    }
    1.98
     karena
    1.95
    Activations Density 0.013%

    No Known Activations