© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39055
    Prev
    Next
    INDEX
    Explanations

    C++ streams and JSON requests

    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
    鹋
    -2.73
    鸲
    -2.63
    </sup>
    -2.42
    </h2>
    -2.33
    section
    -2.20
    ised
    -2.14
    itando
    -2.11
    いかがでしたか
    -2.09
    킁
    -2.09
    儇
    -2.08
    POSITIVE LOGITS
    ]
    2.14
    ers
    2.05
     and
    2.03
     This
    2.02
     gewähr
    1.98
    чен
    1.95
    t
    1.94
     biß
    1.91
    I
    1.89
     it
    1.83
    Activations Density 0.002%

    No Known Activations