© 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. 86715
    Prev
    Next
    INDEX
    Explanations

    address or location specifiers

    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
     schöne
    -1.91
     eigentliche
    -1.84
    翃
    -1.73
     berbagai
    -1.66
     its
    -1.64
     weiße
    -1.63
    乘坐
    -1.61
     obere
    -1.61
     remé
    -1.58
     mittlere
    -1.57
    POSITIVE LOGITS
    you
    1.86
    hhhh
    1.80
     this
    1.70
    hhhhhhhh
    1.69
     jule
    1.65
    when
    1.64
    because
    1.62
     titolata
    1.57
    ؟
    1.54
    although
    1.51
    Activations Density 0.002%

    No Known Activations