© 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. 54
    Prev
    Next
    INDEX
    Explanations

    concepts and their completion

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

    job interview

    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
    provides
    0.39
    state
    0.38
    lld
    0.38
    public
    0.38
    omicide
    0.38
    symbol
    0.37
     ನಗರ
    0.37
    ଚ
    0.37
    automobile
    0.36
    ementerian
    0.36
    POSITIVE LOGITS
    /
    0.51
     وقتی
    0.41
     یا
    0.40
     вообще
    0.38
    ون
    0.37
     devo
    0.37
     جایی
    0.37
     ক্ষেত্রেই
    0.37
     أو
    0.36
     relativamente
    0.36
    Activations Density 2.712%

    No Known Activations