© 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. 543
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     re
    1.16
     miss
    1.16
     absorb
    1.11
     verbal
    1.09
     refine
    1.07
     refer
    1.07
     man
    1.07
     -
    1.06
     moral
    1.06
     limp
    1.05
    POSITIVE LOGITS
    Pentru
    1.96
    Selain
    1.91
    Jangan
    1.84
    Jika
    1.80
    În
    1.78
    Untuk
    1.71
    tidak
    1.70
    Tidak
    1.68
    Dalam
    1.66
    Kemudian
    1.65
    Activations Density 0.002%

    No Known Activations