© 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. 4442
    Prev
    Next
    INDEX
    Explanations

    methods and algorithms

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

    algorithm and techniques

    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
    funcionario
    0.73
    शहर
    0.70
     cidade
    0.70
    🏤
    0.68
     sărb
    0.68
     મહિના
    0.68
    上涨
    0.67
    衙
    0.66
    öffent
    0.65
    rawdę
    0.64
    POSITIVE LOGITS
     method
    1.44
     algorithm
    1.34
     methods
    1.28
     methodology
    1.24
     techniques
    1.23
     algorithms
    1.22
     technique
    1.19
    算法
    1.18
     Algorithm
    1.15
     Method
    1.12
    Activations Density 0.154%

    No Known Activations