© 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. 22-GEMMASCOPE-RES-131K
    7. 73050
    Prev
    Next
    INDEX
    Explanations

    internet slang and digital content

    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
     rowspan
    -1.26
    ものを
    -1.23
     sustainable
    -1.23
    楞
    -1.22
    urnia
    -1.22
    }\
    -1.21
     detrimental
    -1.19
    𝕦
    -1.18
    </sup>
    -1.18
    }-
    -1.16
    POSITIVE LOGITS
    Pä
    1.25
     emoji
    1.25
     funcionam
    1.20
     grupper
    1.20
     egens
    1.20
     rů
    1.17
    klassi
    1.16
    här
    1.15
    FUENTES
    1.13
     ویتامین
    1.13
    Activations Density 0.005%

    No Known Activations