© 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. 70540
    Prev
    Next
    INDEX
    Explanations

    temporal references

    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
    但她
    -1.25
     still
    -1.07
    但他
    -1.00
     others
    -0.99
     mainly
    -0.95
     can
    -0.95
    roffen
    -0.92
    ativistic
    -0.92
    Aiheesta
    -0.92
     можуть
    -0.91
    POSITIVE LOGITS
     when
    1.40
     quando
    1.30
     когда
    1.22
     cuando
    1.16
     lorsqu
    1.13
     عندما
    1.11
     เค
    1.09
    曾
    1.07
     όταν
    1.05
     ketika
    1.02
    Activations Density 0.030%

    No Known Activations