© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103741
    Prev
    Next
    INDEX
    Explanations

    quasars and standard model

    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
    隘
    -1.38
    bilità
    -1.35
    zegovina
    -1.28
    colazione
    -1.27
    ッサン
    -1.18
     dunes
    -1.16
    íqu
    -1.16
    leroi
    -1.15
     کدام
    -1.15
    eled
    -1.15
    POSITIVE LOGITS
     that
    1.37
     nothing
    1.29
    ’
    1.27
     człowiek
    1.26
     okazji
    1.24
    0
    1.24
    O
    1.22
    dáms
    1.21
     nehme
    1.19
     swojej
    1.18
    Activations Density 0.032%

    No Known Activations