© 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-16K
    7. 2120
    Prev
    Next
    INDEX
    Explanations

    combination of factors

    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_16k_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
    er
    1.31
    र
    1.18
    lma
    1.06
    treme
    1.06
     Alemanha
    1.05
    al
    1.04
    ist
    1.03
    ৯
    1.02
     figures
    1.01
     scallops
    1.01
    POSITIVE LOGITS
     출
    1.25
     경
    1.23
    출
    1.22
     접근
    1.20
    BIND
    1.16
     적
    1.16
    வனுக்கு
    1.15
    들의
    1.15
    ⼦
    1.15
    Worth
    1.13
    Activations Density 0.039%

    No Known Activations