© 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. 34-GEMMASCOPE-RES-131K
    7. 84293
    Prev
    Next
    INDEX
    Explanations

    months and seasons

    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_34/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
     yesterday
    -1.19
     especially
    -1.12
    Soon
    -1.10
    很快就
    -1.06
     Soon
    -1.04
    especially
    -1.03
     noong
    -1.03
     Especially
    -1.02
     않는
    -1.01
     fiecare
    -1.00
    POSITIVE LOGITS
     or
    2.03
     if
    1.73
     unless
    1.48
     depending
    1.48
     или
    1.42
     assuming
    1.40
    Assuming
    1.36
     если
    1.27
     Assuming
    1.27
     contingent
    1.25
    Activations Density 0.060%

    No Known Activations