© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9234
    Prev
    Next
    INDEX
    Explanations

    have been

    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
     /
    1.20
     소
    1.15
     e
    1.12
    e
    1.12
    a
    1.11
     là
    1.10
     k
    1.07
    のが
    1.06
     &
    1.06
     y
    1.05
    POSITIVE LOGITS
    castellan
    1.50
    nahi
    1.37
     statesman
    1.36
     metastatic
    1.32
    configuring
    1.31
    mouseleave
    1.30
    renowned
    1.29
     agonizing
    1.28
    linejoin
    1.28
    refrac
    1.28
    Activations Density 0.214%

    No Known Activations