© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8133
    Prev
    Next
    INDEX
    Explanations

    Prior to specific events or entities

    np_acts-logits-general · gemini-2.5-flash-lite

    I am helpful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ud
    0.47
     `
    0.46
     \'
    0.46
     \"
    0.46
    ysh
    0.42
    olo
    0.41
    ::__
    0.41
    .\"
    0.40
    ivet
    0.40
     stor
    0.39
    POSITIVE LOGITS
     Prüfung
    0.82
     Stellung
    0.82
     Vereinig
    0.82
     nachdem
    0.81
     gerade
    0.79
     Zusammen
    0.78
     abhängig
    0.78
     Schrift
    0.78
     Erschein
    0.78
     Hauptstadt
    0.77
    Activations Density 0.007%

    No Known Activations