© 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. 12301
    Prev
    Next
    INDEX
    Explanations

    locations followed by news reports

    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
     apparaître
    -1.30
    kedés
    -1.26
    ními
    -1.25
     tegens
    -1.23
     Испании
    -1.21
    คัญ
    -1.17
    messungen
    -1.16
     waaronder
    -1.16
    mäßigen
    -1.15
    ♭
    -1.15
    POSITIVE LOGITS
    gelang
    1.31
     ۱۳۹
    1.30
     democrá
    1.26
    œuvres
    1.24
     Glaube
    1.24
    子の
    1.24
     they
    1.24
     Grüßen
    1.22
    が
    1.21
     sexuelle
    1.17
    Activations Density 0.021%

    No Known Activations