© 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. 38214
    Prev
    Next
    INDEX
    Explanations

    Colossians book references

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

    Cameroon, Guinea, Gorillas

    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
    識別
    0.43
     دیتا
    0.41
     उत्सुक
    0.41
    horses
    0.40
    띠
    0.40
     gens
    0.40
     sobbing
    0.40
    ⑅
    0.40
     Gens
    0.39
     формата
    0.38
    POSITIVE LOGITS
     Cameroon
    0.79
     Camero
    0.73
     Camer
    0.54
     Vallée
    0.46
    édié
    0.45
    éf
    0.44
    ék
    0.42
     Espagne
    0.42
    ạch
    0.42
    ésar
    0.42
    Activations Density 0.015%

    No Known Activations