© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 587
    Prev
    Next
    INDEX
    Explanations

    words starting with specific letters

    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
     subtle
    1.40
     discrete
    1.32
     `>`,
    1.30
     mobility
    1.26
     simpler
    1.26
     pertain
    1.25
     simple
    1.24
     figuring
    1.24
     narrower
    1.24
     tighter
    1.23
    POSITIVE LOGITS
    blog
    1.05
    Smith
    1.05
    إ
    1.03
    Bever
    1.03
    ab
    1.00
    Andrea
    0.99
    N
    0.99
    v
    0.98
    Kelly
    0.98
    ac
    0.97
    Activations Density 0.729%

    No Known Activations