© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22045
    Prev
    Next
    INDEX
    Explanations

    action games

    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
    </h1>
    -1.30
     into
    -1.19
     Ruß
    -1.06
    </sup>
    -1.05
    </caption>
    -1.02
    nyataan
    -1.01
     at
    -1.00
    トナム
    -0.98
     vraiment
    -0.98
     Insets
    -0.98
    POSITIVE LOGITS
     tiegħek
    1.31
    ający
    1.23
    逦
    1.18
    Amaz
    1.17
     επίσης
    1.16
     keinerlei
    1.16
    환
    1.16
    DISP
    1.13
     you
    1.13
    ie
    1.12
    Activations Density 0.050%

    No Known Activations