© 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. 28490
    Prev
    Next
    INDEX
    Explanations

    pressure gradient

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ↵
    0.48
     Conversely
    0.43
    Tôi
    0.43
    </h3>
    0.43
    ing
    0.43
    </h2>
    0.42
    stone
    0.41
     ກຳ
    0.41
     We
    0.40
     Thiên
    0.39
    POSITIVE LOGITS
    ྰ
    0.43
     LOCCTR
    0.43
    當時
    0.42
    𝙃
    0.42
    栦
    0.41
     больш
    0.41
    当時
    0.41
    ल्फ
    0.41
    後來
    0.40
     μεγά
    0.40
    Activations Density 0.001%

    No Known Activations