© 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. 10-GEMMASCOPE-RES-131K
    4. 123679
    Prev
    Next
    INDEX
    Explanations

    sequences of zeros

    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_10/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
     by
    -1.45
    '
    -1.45
     of
    -1.44
     on
    -1.33
     other
    -1.33
     and
    -1.29
    ,"
    -1.28
     or
    -1.27
     televisor
    -1.27
    ",
    -1.25
    POSITIVE LOGITS
     даже
    1.61
     حدود
    1.48
     wodurch
    1.42
     gebeten
    1.41
     gearbeitet
    1.41
     علاوه
    1.40
     hadapan
    1.40
    Ꮏ
    1.35
     diversas
    1.35
    lysm
    1.34
    Activations Density 0.008%

    No Known Activations