© 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. 129
    Prev
    Next
    INDEX
    Explanations

    period followed by "This"

    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
    
    1.38
    centric
    1.21
    alyse
    1.19
    isation
    1.18
    izes
    1.18
    ifier
    1.12
    ructures
    1.12
    ise
    1.12
    ­
    1.11
    domain
    1.10
    POSITIVE LOGITS
     Also
    2.69
    此外
    2.25
    Also
    2.16
     Ayrıca
    2.13
     That
    2.12
     Alternatively
    2.11
     Otherwise
    2.06
     Additionally
    2.06
     また
    2.05
     Likewise
    2.03
    Activations Density 2.450%

    No Known Activations