© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92235
    Prev
    Next
    INDEX
    Explanations

    UI control declarations and events

    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
     didik
    -1.26
     praktis
    -1.24
     ensimmä
    -1.24
     vokal
    -1.23
     katun
    -1.23
     Además
    -1.20
     rajut
    -1.20
     berge
    -1.19
     coreano
    -1.18
     keindahan
    -1.18
    POSITIVE LOGITS
    }\
    1.35
    </td>
    1.25
    tiéndose
    1.22
    label
    1.22
    </
    1.20
    1.15
     label
    1.15
     Radio
    1.13
     ample
    1.08
    ies
    1.06
    Activations Density 0.000%
    No Known Activations