© 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-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 77298
    Prev
    Next
    INDEX
    Explanations

    code delimiters and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Value
    0.50
     价
    0.48
     Після
    0.46
     무엇
    0.43
    ensureEqual
    0.42
     نہیں
    0.42
    writeValue
    0.41
     அருகே
    0.40
     değeri
    0.40
     вересня
    0.40
    POSITIVE LOGITS
     figsize
    0.44
     redes
    0.43
     максимально
    0.43
     interpretive
    0.41
     FACS
    0.40
     emphasize
    0.39
     **
    0.39
     validate
    0.39
    **
    0.39
     system
    0.39
    Activations Density 0.046%

    No Known Activations