© 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. 22-GEMMASCOPE-RES-131K
    7. 65246
    Prev
    Next
    INDEX
    Explanations

    I/you statements

    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_22/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
    ∽
    -1.22
    ˃
    -1.16
    应该
    -1.14
    ⭐️⭐️
    -1.10
     Hentet
    -1.06
    💫
    -1.05
    Pand
    -1.05
    一样
    -1.05
    我们
    -1.04
    ℅
    -1.04
    POSITIVE LOGITS
     biggest
    1.38
    Gön
    1.33
     Übernach
    1.29
     ponieważ
    1.22
    𝙢
    1.20
    ͋
    1.20
     roughly
    1.20
    pontos
    1.18
     redor
    1.17
     since
    1.16
    Activations Density 0.102%

    No Known Activations