© 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. 9882
    Prev
    Next
    INDEX
    Explanations

    <email@asu.edu>

    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
     sollten
    -1.32
    :
    
    -1.30
     immagine
    -1.27
     sollte
    -1.26
     possa
    -1.26
     pudesse
    -1.25
    ……」
    -1.23
     realice
    -1.22
    ?»
    -1.20
     the
    -1.19
    POSITIVE LOGITS
    8
    1.60
    6
    1.49
    7
    1.45
    5
    1.31
    4
    1.27
     verlangt
    1.16
    2
    1.15
    ardonnay
    1.14
    _
    1.13
    られていた
    1.13
    Activations Density 0.151%

    No Known Activations