© 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. 34-GEMMASCOPE-RES-131K
    7. 55864
    Prev
    Next
    INDEX
    Explanations

    identifying and specifying

    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
    S
    -1.55
    ↵
    -1.33
    ↵↵
    -1.27
    F
    -1.27
    2
    -1.27
    意思是
    -1.23
    <strong>
    -1.23
    8
    -1.21
    D
    -1.20
    en
    -1.16
    POSITIVE LOGITS
     sebagai
    1.71
    鐒
    1.53
     and
    1.45
    おわりに
    1.39
    #)
    1.39
    щихся
    1.38
     identificado
    1.34
    asında
    1.34
    訖
    1.33
    havior
    1.31
    Activations Density 0.080%

    No Known Activations