© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75712
    Prev
    Next
    INDEX
    Explanations

    scores and ranks

    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
    if
    -1.34
     if
    -1.30
     for
    -1.25
    skiego
    -1.17
    𝐙
    -1.16
    ブリッド
    -1.12
     huis
    -1.09
    OTP
    -1.06
     盆
    -1.06
    /****
    -1.05
    POSITIVE LOGITS
     häufig
    1.59
    налу
    1.27
     these
    1.25
     each
    1.23
    </h1>
    1.19
     this
    1.17
     cũng
    1.16
     meditación
    1.15
     our
    1.13
    dimer
    1.09
    Activations Density 0.047%

    No Known Activations