© 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. 79168
    Prev
    Next
    INDEX
    Explanations

    citations with author names

    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
     kupa
    -1.34
     saati
    -1.23
     Kese
    -1.16
     kutu
    -1.13
     Jasa
    -1.12
     diki
    -1.09
     hakim
    -1.09
     microfibra
    -1.08
     sabun
    -1.08
     bunda
    -1.08
    POSITIVE LOGITS
     pamoja
    1.22
     https
    1.10
     intertwined
    1.06
     inaweza
    1.05
     including
    1.05
     ambao
    1.03
     appropriately
    1.02
     habari
    1.00
    ociação
    0.98
     similarly
    0.97
    Activations Density 0.037%

    No Known Activations