© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14555
    Prev
    Next
    INDEX
    Explanations

    initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     شبه
    0.37
     exporter
    0.37
    𝜎
    0.37
    料理
    0.37
     emerald
    0.36
     splitpos
    0.36
    ⏭
    0.36
     rustic
    0.36
    髦
    0.36
    IDER
    0.35
    POSITIVE LOGITS
     initialization
    1.20
     Initialization
    1.17
    Initialization
    1.16
     initialize
    1.13
     initializes
    1.13
    initialize
    1.09
    初始化
    1.07
     初始化
    1.06
    Initialize
    1.05
     Initialize
    1.02
    Activations Density 0.288%

    No Known Activations