© 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. 75972
    Prev
    Next
    INDEX
    Explanations

    questions after punctuation

    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
     tänka
    -1.02
    enziali
    -0.96
     vrou
    -0.93
     obro
    -0.93
    setValue
    -0.93
     tė
    -0.92
     ур
    -0.88
    assertThat
    -0.87
     samen
    -0.86
     gouttes
    -0.85
    POSITIVE LOGITS
     you
    3.20
     your
    2.63
     if
    1.78
     stop
    1.69
     please
    1.66
     why
    1.56
    If
    1.53
     do
    1.51
    Your
    1.46
    Are
    1.45
    Activations Density 0.031%

    No Known Activations