© 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. 9873
    Prev
    Next
    INDEX
    Explanations

    hash code objects size

    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
     ajustado
    -1.63
     describir
    -1.43
     líquidos
    -1.40
    踞
    -1.36
     sellado
    -1.32
    lında
    -1.30
    逦
    -1.30
    wendige
    -1.28
     internetowa
    -1.26
     músculos
    -1.26
    POSITIVE LOGITS
    我才
    1.30
     terdekat
    1.17
     “
    1.16
     these
    1.13
    他才
    1.12
    ls
    1.09
    它的
    1.08
     інших
    1.02
     wherea
    1.02
     других
    1.02
    Activations Density 0.021%

    No Known Activations