© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51
    Prev
    Next
    INDEX
    Explanations

    againstlabuscis

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

    structured technical tutorial content, especially programming how‑tos with section headings, numbered/bulleted steps, code snippets, and documentation URLs.

    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
     воспита
    0.20
     言っ
    0.20
     ],"
    0.19
    [,,"
    0.19
     কাপড়
    0.19
    Lycodon
    0.19
    󰀄
    0.19
     سرطان
    0.19
     बल्लेबाज
    0.19
    }^{+}+
    0.19
    POSITIVE LOGITS
     high
    0.21
     the
    0.20
     nuova
    0.19
    ની
    0.19
     novos
    0.19
     XYZ
    0.19
     was
    0.18
     standard
    0.18
     portfolios
    0.18
     were
    0.18
    Activations Density 3.310%

    No Known Activations