© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98087
    Prev
    Next
    INDEX
    Explanations

    variations from and between

    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
    ཇ
    -0.82
     начале
    -0.81
     inbound
    -0.79
    prefixer
    -0.77
     chickens
    -0.75
    Nederland
    -0.75
    бые
    -0.75
    FunctionType
    -0.74
     ろ
    -0.74
    yasi
    -0.74
    POSITIVE LOGITS
     from
    3.98
     between
    2.91
     From
    1.98
     từ
    1.95
    From
    1.91
    from
    1.84
     между
    1.76
    between
    1.73
    从
    1.71
    從
    1.65
    Activations Density 0.082%

    No Known Activations