© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93798
    Prev
    Next
    INDEX
    Explanations

    Here's followed by introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     этом
    -1.25
     этой
    -1.23
    ⬥
    -1.21
     geloof
    -1.20
    abaikan
    -1.18
    ˾
    -1.16
     этих
    -1.15
    poptotic
    -1.13
    뺄
    -1.11
    ≀
    -1.11
    POSITIVE LOGITS
     how
    2.55
     a
    2.44
     hoping
    2.23
     what
    2.00
     where
    1.83
     why
    1.69
     your
    1.55
     an
    1.51
     something
    1.51
     another
    1.50
    Activations Density 0.042%

    No Known Activations