© 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. 178
    Prev
    Next
    INDEX
    Explanations

    it was

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

    it's a

    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
    เลือก
    0.17
     。
    0.17
     selector
    0.17
     イン
    0.17
    。\
    0.16
    '.
    0.16
    の中に
    0.16
     ।
    0.16
    ।
    0.16
    .*
    0.15
    POSITIVE LOGITS
     isn
    0.24
     wasn
    0.24
     beho
    0.24
     seems
    0.23
     really
    0.22
     happened
    0.22
     happens
    0.22
     doesn
    0.21
     wouldn
    0.20
     είναι
    0.20
    Activations Density 1.499%

    No Known Activations