© 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. 31-GEMMASCOPE-2-RES-16K
    7. 14368
    Prev
    Next
    INDEX
    Explanations

    location of your

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

    moving perspective

    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_31_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
    ّد
    0.46
    payroll
    0.43
    ピンク
    0.42
    рец
    0.40
    幵
    0.40
     führ
    0.40
    స్టు
    0.40
    itl
    0.40
     männ
    0.39
    Haupt
    0.39
    POSITIVE LOGITS
     onda
    0.46
    ợ
    0.46
     MINISTER
    0.46
    ya
    0.45
     Everyone
    0.44
     sống
    0.44
     hozzá
    0.44
    NEY
    0.44
    DEBUG
    0.43
     hilo
    0.43
    Activations Density 0.001%

    No Known Activations