© 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. 512
    Prev
    Next
    INDEX
    Explanations

    URLs for information and resources

    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
     To
    0.88
     Be
    0.88
    A
    0.85
     Take
    0.85
     Day
    0.84
     No
    0.83
    O
    0.83
     Har
    0.82
     All
    0.80
     New
    0.79
    POSITIVE LOGITS
    castruct
    1.10
    estrutura
    1.04
    ufieurs
    1.03
    <unused0>
    1.03
    oksatta
    1.02
    iftoire
    1.01
    akkhati
    1.01
    𒄠
    1.00
     spaceleft
    0.98
     kttt
    0.98
    Activations Density 0.068%

    No Known Activations