© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 4307
    Prev
    Next
    INDEX
    Explanations

    exclamations or questions

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

    The neuron detects enthusiastic, upbeat language—greetings, encouragements, and excited/positive expressions.

    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_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
     wobei
    0.43
     undisclosed
    0.41
     dehuman
    0.38
     r
    0.38
    தாகவும்
    0.38
     Wsp
    0.38
     вследствие
    0.38
    repository
    0.37
     subdued
    0.37
     .,
    0.37
    POSITIVE LOGITS
    !
    2.36
    !
    2.20
    !)
    1.92
    !”
    1.88
    !).
    1.85
    !"
    1.84
    !</
    1.84
    !")
    1.82
    !“
    1.78
    !");
    1.75
    Activations Density 0.483%

    No Known Activations