© 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. 22-GEMMASCOPE-RES-131K
    7. 67022
    Prev
    Next
    INDEX
    Explanations

    frames, coordinates, and spaces

    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
     alcune
    -1.16
     percentage
    -1.10
     обеспечи
    -1.09
     amazing
    -1.09
     occuper
    -1.08
     quintessential
    -1.07
     crucial
    -1.06
     molti
    -1.05
     die
    -1.04
     majestic
    -1.04
    POSITIVE LOGITS
     kenal
    1.48
     consultato
    1.28
     keterampilan
    1.27
     selera
    1.16
     with
    1.16
     интерьера
    1.14
    ᅠ
    1.13
    ásticos
    1.13
    İY
    1.10
     permitan
    1.09
    Activations Density 0.027%

    No Known Activations