© 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. 136413
    Prev
    Next
    INDEX
    Explanations

    paths, how many, embodiment of, since dead, means turf

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

    specialized terms (proteins, agency, populations)

    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
    При
    0.52
    ꔹ
    0.48
    Пре
    0.48
     ภาพ
    0.45
    Из
    0.45
    下图
    0.44
     при
    0.43
    י
    0.43
    На
    0.43
     სამ
    0.43
    POSITIVE LOGITS
     poblaciones
    0.50
    考え
    0.46
     individuo
    0.45
    pital
    0.45
     personnaliser
    0.43
    holder
    0.43
     Cient
    0.42
    ياء
    0.41
     comunidades
    0.40
    veu
    0.39
    Activations Density 0.001%

    No Known Activations