© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90289
    Prev
    Next
    INDEX
    Explanations

    Corinthians references

    np_acts-logits-general · gemini-2.5-flash-lite

    monadic functors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     न्यूमेरिकल
    0.45
    exclusions
    0.44
     помещение
    0.43
    ändert
    0.43
    ellipse
    0.43
    姶
    0.42
    ENTAL
    0.42
     DJs
    0.42
     voic
    0.41
     एसएमएस
    0.41
    POSITIVE LOGITS
    Arche
    0.52
    Dogs
    0.48
     Arche
    0.47
     coalgebra
    0.47
     functor
    0.46
    🐕
    0.46
     Dogs
    0.45
     archetype
    0.45
    Failure
    0.44
     cats
    0.43
    Activations Density 0.027%

    No Known Activations