© 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. 40-GEMMASCOPE-2-RES-262K
    7. 995
    Prev
    Next
    INDEX
    Explanations

    astrology, frequency, console, path, tensors, metrics

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

    the neuron detects salient/content-bearing words (key topic or emphasis tokens) in the text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    و
    0.53
    ים
    0.43
    崤
    0.39
    یی
    0.39
    ির
    0.37
    اا
    0.37
    وث
    0.37
    δες
    0.37
    라서
    0.37
    ك
    0.36
    POSITIVE LOGITS
     ២
    0.44
     ibid
    0.40
    {}".
    0.39
     ú
    0.38
     historia
    0.38
     Ibid
    0.37
     jedynie
    0.37
     others
    0.36
     aplik
    0.36
    ]
    0.36
    Activations Density 0.754%

    No Known Activations