© 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. 59963
    Prev
    Next
    INDEX
    Explanations

    points per game or resolution units

    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
     setAddress
    -0.79
    dBm
    -0.78
    MeV
    -0.78
    Ghz
    -0.75
    kDa
    -0.75
     superior
    -0.74
     cayó
    -0.71
     utilizzata
    -0.71
     Turm
    -0.70
    しば
    -0.69
    POSITIVE LOGITS
    PPS
    1.31
     PPS
    1.30
     DPS
    1.20
    ppp
    1.18
     BPS
    1.17
     per
    1.16
     fps
    1.15
    pps
    1.11
    fps
    1.09
     dps
    1.09
    Activations Density 0.080%

    No Known Activations