© 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. 10-GEMMASCOPE-RES-131K
    7. 648
    Prev
    Next
    INDEX
    Explanations

    increase, change, evolve, develop

    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_10/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
     スクエア
    -1.65
    酗
    -1.65
     of
    -1.63
     associées
    -1.63
    ik
    -1.55
     alſo
    -1.55
     rafraî
    -1.52
    bildung
    -1.52
     отредакти
    -1.52
    ें
    -1.51
    POSITIVE LOGITS
     into
    2.69
     in
    2.13
     We
    1.80
    ulisan
    1.64
     Benutz
    1.59
    )
    1.54
    etsk
    1.51
    icona
    1.51
    掟
    1.50
    軋
    1.50
    Activations Density 0.350%

    No Known Activations