© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3121
    Prev
    Next
    INDEX
    Explanations

    explaining mechanisms or requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *,
    0.73
    1
    0.73
    \*
    0.65
    ind
    0.62
    ∙
    0.62
    ၊
    0.60
    ·
    0.60
     לג
    0.60
    raf
    0.59
    \",
    0.58
    POSITIVE LOGITS
    ஜ்மஹ
    0.74
    ையாள
    0.73
     décor
    0.73
    ికె
    0.72
     قائد
    0.72
    ᖕ
    0.71
     halibut
    0.70
    </footer>
    0.70
     wearable
    0.70
     decorator
    0.70
    Activations Density 0.174%

    No Known Activations