© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 299
    Prev
    Next
    INDEX
    Explanations

    steps and cited information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
     lawfully
    1.27
    ↵↵
    1.26
     delicacy
    1.10
     either
    1.07
     اسم
    1.06
     singly
    1.05
     nitrates
    1.05
     swords
    1.02
     jot
    1.02
     belirli
    1.01
    POSITIVE LOGITS
    mlabeledtr
    1.81
    伀
    1.74
    푚
    1.69
    aprendizaje
    1.66
    esquerda
    1.65
    isteren
    1.64
    updateConfirm
    1.63
    getAddress
    1.63
    Density
    1.63
    getProgress
    1.63
    Activations Density 0.000%

    No Known Activations