© 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. 85459
    Prev
    Next
    INDEX
    Explanations

    separators in news datelines

    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
     compartida
    -1.28
     would
    -1.26
     words
    -1.26
     explores
    -1.24
     😂
    -1.23
     detalló
    -1.20
     vielmehr
    -1.19
     compuesta
    -1.16
     sodass
    -1.16
     describe
    -1.14
    POSITIVE LOGITS
     fren
    1.34
     étan
    1.30
     negru
    1.30
    ↵
    1.28
    Vlast
    1.22
     précie
    1.20
     fallu
    1.20
    Hlav
    1.16
     作り方
    1.16
     eventuell
    1.16
    Activations Density 0.099%

    No Known Activations