© 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. 65039
    Prev
    Next
    INDEX
    Explanations

    Root followed by identifier or type

    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
    u
    -3.16
    しました
    -2.28
    ',
    -2.25
    したので
    -2.22
    でしたが
    -2.22
     he
    -2.20
    ]$.
    -2.16
    텃
    -2.16
    i
    -2.09
     харак
    -2.05
    POSITIVE LOGITS
    槩
    2.98
    AN
    2.98
     ataupun
    2.91
    AL
    2.84
    </strong>
    2.84
    ED
    2.64
    Additionally
    2.64
    ୌ
    2.58
     și
    2.50
    或
    2.50
    Activations Density 0.010%

    No Known Activations