© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 16329
    Prev
    Next
    INDEX
    Explanations

    time duration

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

    time or step followed by punctuation

    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
     देण्यासाठी
    0.40
     ():
    0.40
    ,《
    0.38
     de
    0.38
    tellers
    0.36
    证券投资基金
    0.35
     seduced
    0.35
    -
    0.35
    :",
    0.34
     fiercely
    0.34
    POSITIVE LOGITS
    )
    0.38
    ᅵ
    0.36
    ]
    0.35
    য়িক
    0.34
     endophytic
    0.34
     kraja
    0.33
    ↵
    0.33
    ικά
    0.33
     tanning
    0.33
    0
    0.33
    Activations Density 1.268%

    No Known Activations