© 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. 34-GEMMASCOPE-RES-131K
    7. 117375
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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_34/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
     tuvimos
    -1.26
     Mischung
    -1.20
    eload
    -1.20
    Sì
    -1.19
     empezaron
    -1.16
    だったので
    -1.16
    Così
    -1.14
     pegatinas
    -1.13
    ünkü
    -1.10
    pergillus
    -1.10
    POSITIVE LOGITS
    as
    1.08
    both
    1.05
    am
    1.05
    os
    1.03
    la
    1.01
    ⤒
    1.00
     ,.
    0.97
    ti
    0.96
    re
    0.96
    un
    0.94
    Activations Density 0.163%

    No Known Activations