© 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. 102553
    Prev
    Next
    INDEX
    Explanations

    requirement of or for

    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
    \
    -1.56
    )
    -1.50
    A
    -1.38
    许多
    -1.14
    ."
    -1.13
     chronicles
    -1.12
    “
    -1.11
     endeavors
    -1.09
    幾乎
    -1.07
     mehrere
    -1.05
    POSITIVE LOGITS
     for
    1.59
     of
    1.52
    酲
    1.29
     adanya
    1.28
     minimale
    1.27
    嵎
    1.21
    怍
    1.20
    鰾
    1.17
    晖
    1.17
     to
    1.17
    Activations Density 0.036%

    No Known Activations