© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14958
    Prev
    Next
    INDEX
    Explanations

    one versus the other

    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_7_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
    ni
    2.16
    σία
    2.01
    ᾽
    1.98
    stoff
    1.97
    na
    1.94
    sc
    1.88
    Suk
    1.85
    מצא
    1.84
     Svet
    1.82
    ție
    1.78
    POSITIVE LOGITS
    "،
    2.26
    ।"
    2.21
     seventy
    2.18
     eighty
    2.18
    "<
    2.16
    。"
    2.15
    "।
    2.11
     ٣
    2.08
     ."
    2.05
     sixty
    2.02
    Activations Density 0.027%

    No Known Activations