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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12273
    Prev
    Next
    INDEX
    Explanations

    active phrases and clauses

    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
     innova
    -1.22
     suav
    -1.15
     vitu
    -1.13
     causative
    -1.12
     abor
    -1.09
     parla
    -1.07
     jurk
    -1.07
     experim
    -1.07
     effici
    -1.05
     encom
    -1.05
    POSITIVE LOGITS
     pimpinan
    1.05
     and
    1.04
     besonder
    1.03
     participado
    0.96
     calificaciones
    0.96
     mercancías
    0.95
     estadounidenses
    0.95
     atasan
    0.94
     conseguido
    0.94
     Gründe
    0.94
    Activations Density 0.092%

    No Known Activations