© 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. 1510
    Prev
    Next
    INDEX
    Explanations

    consult with healthcare professional

    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
    reas
    1.32
    gan
    1.17
    <0xAC>
    1.08
    lea
    1.05
    namese
    1.04
    perf
    1.04
    yla
    1.02
    行
    1.02
    wne
    1.02
    getField
    1.02
    POSITIVE LOGITS
     SIINFEKL
    1.12
    Bankr
    1.12
     YA
    1.08
     मिलियन
    1.07
     trous
    1.07
     diferenças
    1.03
    جس
    1.03
    ଵ
    1.02
     cathodic
    1.02
     fabricación
    1.01
    Activations Density 0.004%

    No Known Activations