© 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. 21842
    Prev
    Next
    INDEX
    Explanations

    born in

    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
    <bos>
    -1.81
    prende
    -1.46
     your
    -1.44
    $<$
    -1.40
    proz
    -1.38
    
    -1.38
    DOCTYPE
    -1.37
     Profesor
    -1.33
     gambar
    -1.32
    练习
    -1.30
    POSITIVE LOGITS
     there
    1.60
    .
    1.51
    することも
    1.45
     through
    1.43
    只剩下
    1.40
    These
    1.38
     seiner
    1.37
    pagnol
    1.33
    these
    1.32
    gdala
    1.31
    Activations Density 0.032%

    No Known Activations