© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39012
    Prev
    Next
    INDEX
    Explanations

    locations for events

    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
    {
    -0.99
    能够
    -0.99
    しまって
    -0.94
     hvilken
    -0.94
    ϑ
    -0.93
    Deletes
    -0.93
     diferite
    -0.90
     hvilke
    -0.90
     demarcation
    -0.88
    onai
    -0.88
    POSITIVE LOGITS
     at
    1.50
     of
    1.47
     rompecabezas
    1.26
     digunakan
    1.22
    ]):
    1.20
    かわらず
    1.18
     defensor
    1.14
     other
    1.13
     bús
    1.12
    enderror
    1.11
    Activations Density 0.018%

    No Known Activations