© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42255
    Prev
    Next
    INDEX
    Explanations

    technical and scientific contexts

    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
     skóra
    -1.26
    Their
    -1.23
     möglichst
    -1.23
     deje
    -1.16
     only
    -1.16
     verbre
    -1.14
     hauptsächlich
    -1.12
     schützen
    -1.10
     assin
    -1.09
    iscono
    -1.06
    POSITIVE LOGITS
     defStyle
    1.23
     –
    1.18
    heden
    1.13
     sondern
    1.12
    beeld
    1.11
    ræ
    1.08
     εικό
    1.05
     ideen
    1.05
     Ş
    1.05
    YesNo
    1.04
    Activations Density 0.263%

    No Known Activations