© 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. 16-GEMMASCOPE-2-RES-262K
    7. 46508
    Prev
    Next
    INDEX
    Explanations

    do return

    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_16_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
    ad
    0.68
    ου
    0.66
     wichtig
    0.64
     enhances
    0.63
    cient
    0.63
    _
    0.63
    était
    0.61
     can
    0.60
    ש
    0.60
    ia
    0.59
    POSITIVE LOGITS
     GoObject
    0.66
     금
    0.63
    이지만
    0.62
     संसदीय
    0.61
    кти
    0.58
     размеров
    0.57
     کیونکہ
    0.57
    这一点
    0.57
     certes
    0.57
     없
    0.57
    Activations Density 0.001%

    No Known Activations