© 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. 119134
    Prev
    Next
    INDEX
    Explanations

    supra and infra references

    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
    重生
    -0.75
    attribs
    -0.71
     actionTypes
    -0.68
     گردد
    -0.68
     midline
    -0.67
    tring
    -0.66
     motivation
    -0.66
     piel
    -0.66
    寒冷
    -0.66
    Athena
    -0.66
    POSITIVE LOGITS
     supra
    4.09
    supra
    3.42
     infra
    3.00
     Supra
    2.63
    infra
    2.59
    Sup
    2.11
     Infra
    2.05
    Infra
    1.98
    upra
    1.80
    sup
    1.76
    Activations Density 0.040%

    No Known Activations