© 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-65K
    7. 17095
    Prev
    Next
    INDEX
    Explanations

    collective nouns following our

    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_65k_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
    ’
    0.74
    0.70
     হয়তো
    0.65
    `
    0.61
    ス
    0.61
     had
    0.59
    เป็น
    0.59
     puede
    0.58
     arrived
    0.58
     поверну
    0.58
    POSITIVE LOGITS
     ہمیں
    0.55
    iour
    0.52
    ung
    0.51
    的存在
    0.50
    မြင်
    0.50
    ite
    0.49
    ear
    0.49
    ad
    0.49
    ant
    0.49
    𝟰
    0.49
    Activations Density 0.044%

    No Known Activations