© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13908
    Prev
    Next
    INDEX
    Explanations

    nicknamed phrases like "_______ of the _______"

    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_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
    *}
    0.43
     vattati
    0.42
    য়েড
    0.40
    :=
    0.40
    하실
    0.38
    ɻ
    0.37
    dplyr
    0.36
     natthi
    0.36
     coerc
    0.35
    传播
    0.35
    POSITIVE LOGITS
     nicknamed
    0.96
     ‘
    0.85
     “
    0.81
     dubbed
    0.74
     jewel
    0.74
     '
    0.73
     \"
    0.73
     "
    0.72
     king
    0.71
     „
    0.68
    Activations Density 0.042%

    No Known Activations