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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 15230
    Prev
    Next
    INDEX
    Explanations

    used to be

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

    things that used to be

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

    used to be

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_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
    其
    0.59
     its
    0.57
     nuevas
    0.55
     newNode
    0.55
     (
    0.54
     reconnect
    0.53
    ਰ
    0.53
    を果た
    0.50
    RIST
    0.50
     ones
    0.49
    POSITIVE LOGITS
     autrefois
    0.95
    ᱖
    0.63
    only
    0.62
    formerly
    0.61
    problem
    0.60
    hört
    0.60
     только
    0.60
    anyone
    0.60
     단순히
    0.59
     тільки
    0.59
    Activations Density 0.573%

    No Known Activations