© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11264
    Prev
    Next
    INDEX
    Explanations

    others

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

    referring to previous or subsequent entities

    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_40_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
    ·
    0.39
     ·
    0.37
    /*
    0.36
     these
    0.36
    â
    0.35
     estes
    0.34
     —
    0.33
    ↵↵
    0.33
    ↵↵↵
    0.33
    »
    0.33
    POSITIVE LOGITS
    后者
    1.08
     latter
    0.91
     éste
    0.88
     उससे
    0.82
     ésta
    0.80
     dessen
    0.80
     thereof
    0.78
     उसको
    0.78
     उसमें
    0.77
     அவரை
    0.76
    Activations Density 2.374%

    No Known Activations