© 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. 17-GEMMASCOPE-2-RES-16K
    4. 2184
    Prev
    Next
    INDEX
    Explanations

    why it's / crucial

    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
    」
    1.19
     banknotes
    1.19
    自殺
    1.14
    下列
    1.14
     centena
    1.11
    汽车
    1.10
     ‫
    1.09
    汽車
    1.08
     unauthorised
    1.08
    建筑物
    1.08
    POSITIVE LOGITS
     foundational
    1.80
     kiddos
    1.76
     nuanced
    1.75
     uptick
    1.68
     figuring
    1.53
     vibe
    1.53
     prioritization
    1.51
     nuance
    1.49
     prioritizing
    1.46
     shenanigans
    1.45
    Activations Density 0.773%

    No Known Activations