© 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. 194702
    Prev
    Next
    INDEX
    Explanations

    organizational structure

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

    GPT-4

    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
     quadrado
    0.49
     quoi
    0.47
     quadrados
    0.47
     coincid
    0.44
    з
    0.44
    にも
    0.44
    к
    0.44
    据
    0.43
     selbst
    0.43
    漢
    0.43
    POSITIVE LOGITS
    SetConfig
    0.54
     أع
    0.46
     (’
    0.45
    anın
    0.45
     організації
    0.44
     )\
    0.44
     なかっ
    0.44
    Ml
    0.44
    IsEnabled
    0.43
     organisational
    0.43
    Activations Density 0.000%

    No Known Activations