© 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. 16162
    Prev
    Next
    INDEX
    Explanations

    stocking, equipment, oral, styles

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

    identification documents

    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
    ’
    0.55
     bulun
    0.49
     fragen
    0.48
    éc
    0.48
     erscheinen
    0.46
     niemand
    0.46
     be
    0.45
     berichtet
    0.45
    拠
    0.45
     vraag
    0.44
    POSITIVE LOGITS
    ente
    0.46
    თა
    0.45
    嵯
    0.45
    Ⲧ
    0.44
    िक्की
    0.44
    🏄
    0.44
    ructured
    0.43
    ಶ
    0.43
     చేసి
    0.42
    差
    0.42
    Activations Density 0.006%

    No Known Activations