© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2059
    Prev
    Next
    INDEX
    Explanations

    names or titles followed by last names

    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_17_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
    𒌷
    2.06
    𒌉
    2.04
    𒉈
    2.03
    𒆪
    2.03
    asaddo
    2.03
    𒄩
    2.02
    𒆕
    2.00
    𒂍
    1.98
    𒄿
    1.98
    𒋼
    1.98
    POSITIVE LOGITS
     K
    1.38
     H
    1.38
     S
    1.35
     T
    1.34
     D
    1.33
     L
    1.32
     R
    1.31
     F
    1.27
     G
    1.25
     C
    1.25
    Activations Density 0.816%

    No Known Activations