© 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. 37937
    Prev
    Next
    INDEX
    Explanations

    marks or marked dates

    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
    mittlung
    -0.87
     instruk
    -0.82
    メージ
    -0.79
    uginosa
    -0.77
    𝕎
    -0.76
    Examples
    -0.76
    ịnh
    -0.75
     シルエット
    -0.75
    🔆
    -0.74
     exhibición
    -0.74
    POSITIVE LOGITS
     marks
    5.34
     marking
    4.59
     mark
    4.53
     marked
    3.97
    marks
    3.78
    Marking
    3.44
    marking
    3.41
    mark
    3.31
     Marking
    3.28
    Marks
    3.20
    Activations Density 0.179%

    No Known Activations