© 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. 22-GEMMASCOPE-RES-131K
    7. 9512
    Prev
    Next
    INDEX
    Explanations

    cannot do something

    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_22/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
    schwar
    -1.48
    vielen
    -1.42
    Gön
    -1.38
    Öl
    -1.37
     排骨
    -1.34
    Tämä
    -1.34
     花纹
    -1.34
    
    -1.34
     femininas
    -1.34
    bicicleta
    -1.34
    POSITIVE LOGITS
    i
    2.05
    an
    1.88
    t
    1.78
    u
    1.67
     be
    1.64
    n
    1.59
    S
    1.59
    e
    1.59
    T
    1.54
    ar
    1.53
    Activations Density 0.038%

    No Known Activations