© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13217
    Prev
    Next
    INDEX
    Explanations

    null terminator `\0`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     spoiled
    1.72
    üsse
    1.68
    ⵍ
    1.67
    farande
    1.63
     aluminio
    1.58
    imals
    1.51
    üz
    1.48
     spoilt
    1.47
     flancs
    1.45
    ِس
    1.45
    POSITIVE LOGITS
     We
    1.96
    We
    1.96
     นอกจาก
    1.88
     These
    1.87
    窕
    1.86
     Although
    1.85
     For
    1.84
     This
    1.82
     น
    1.82
     ใน
    1.78
    Activations Density 0.000%

    No Known Activations