© 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. 113553
    Prev
    Next
    INDEX
    Explanations

    signals and alerts

    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
     abbildung
    -1.29
     сына
    -1.27
     تمامی
    -1.13
    美丽的
    -1.09
     glaub
    -1.09
    蝇
    -1.08
     avanzada
    -1.07
     serán
    -1.07
     renown
    -1.06
     administrativo
    -1.05
    POSITIVE LOGITS
     need
    1.48
    谖
    1.43
     an
    1.21
    襌
    1.19
     parteci
    1.19
    ness
    1.19
    enged
    1.18
     indication
    1.16
     was
    1.15
     indicate
    1.15
    Activations Density 0.103%

    No Known Activations