© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49346
    Prev
    Next
    INDEX
    Explanations

    perfect intervals

    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
     хозяйства
    -0.78
    mixer
    -0.76
    ให
    -0.76
    ర
    -0.74
     Mixer
    -0.74
     Topf
    -0.73
     mixers
    -0.73
    汴
    -0.72
    Mixer
    -0.72
     niew
    -0.71
    POSITIVE LOGITS
     interval
    1.39
     intervals
    1.26
     perfect
    1.20
    intervals
    1.20
    Interval
    1.15
     Perfect
    1.15
     Intervals
    1.14
     Interval
    1.11
    Perfect
    1.06
    perfect
    1.05
    Activations Density 0.013%

    No Known Activations