© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12183
    Prev
    Next
    INDEX
    Explanations

    the latest

    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
     Projektu
    -1.36
     ralla
    -1.17
    が
    -1.16
    テク
    -1.13
     luminoso
    -1.11
     deaktivi
    -1.10
     cerro
    -1.10
     liquido
    -1.10
    Tinh
    -1.10
    を
    -1.09
    POSITIVE LOGITS
     campañas
    1.30
     обладает
    1.27
    homonymie
    1.26
    礻
    1.25
    一定的
    1.24
    唧
    1.22
     určit
    1.20
     ciertas
    1.19
     olhar
    1.19
     certain
    1.19
    Activations Density 0.061%

    No Known Activations