Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 36615
    Prev
    Next
    INDEX
    Explanations

    Okay, let's talk about

    np_acts-logits-general · gemini-2.5-flash-lite

    the start of an assistant’s reply, especially introductory framing that sets up the discussion of the user’s topic.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    ástica
    0.48
    ᵒ
    0.46
     jeopard
    0.46
     bolstered
    0.44
     Fiona
    0.43
    جوم
    0.43
     goi
    0.43
    سی
    0.42
    ພວກ
    0.42
    擋
    0.42
    POSITIVE LOGITS
     parlament
    0.41
    धिकरण
    0.40
    harma
    0.40
     ellipse
    0.39
     kontinuier
    0.39
    esh
    0.38
     contributes
    0.38
    sometimes
    0.38
    iye
    0.38
     Gemeinschaft
    0.38
    Activations Density 0.005%

    No Known Activations