© 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. 22380
    Prev
    Next
    INDEX
    Explanations

    mood and quality descriptors

    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
     MUCH
    -2.88
    ).
    -2.78
    衚
    -2.72
    ”.
    -2.55
    </td>
    -2.48
    皷
    -2.39
    挣
    -2.38
    きちんと
    -2.36
     評価
    -2.30
     Heute
    -2.28
    POSITIVE LOGITS
     necessities
    2.63
    🢒
    2.58
    旅程
    2.42
    ꪔ
    2.30
     varmt
    2.28
    ！”
    2.27
    🐶
    2.27
    𓋼
    2.25
     grå
    2.19
    лили
    2.19
    Activations Density 0.002%

    No Known Activations