© 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. 83352
    Prev
    Next
    INDEX
    Explanations

    force of

    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
     defectos
    -1.09
     \"
    -1.03
    \
    -1.02
     flawless
    -1.02
     amores
    -1.00
     oficio
    -1.00
    ⇗
    -0.99
     muros
    -0.99
     аккура
    -0.96
    THEORY
    -0.96
    POSITIVE LOGITS
     majeure
    1.44
     první
    1.03
     demselben
    1.02
     intenta
    1.02
     of
    0.98
    well
    0.93
     denselben
    0.93
     invokingState
    0.93
     нового
    0.93
     jub
    0.93
    Activations Density 0.016%

    No Known Activations