© 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. 33118
    Prev
    Next
    INDEX
    Explanations

    day 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
    össä
    -1.11
     protoimpl
    -1.03
     galima
    -0.99
    füllen
    -0.96
    ]));
    -0.96
    ก่อน
    -0.96
    台風
    -0.95
     dưới
    -0.95
    ידה
    -0.94
    ถ้า
    -0.94
    POSITIVE LOGITS
     day
    1.34
     noon
    1.23
     Sun
    1.23
     sunrise
    1.20
     December
    1.20
     daylight
    1.19
     summer
    1.16
     north
    1.16
     at
    1.13
     night
    1.10
    Activations Density 0.044%

    No Known Activations