© 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. 100168
    Prev
    Next
    INDEX
    Explanations

    banker, erect, cache

    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
    ierra
    0.55
    лово
    0.52
    Г
    0.50
    Во
    0.50
    uyentes
    0.49
    Е
    0.48
    헙
    0.48
    ંટ
    0.48
    ueel
    0.47
    クレジット
    0.47
    POSITIVE LOGITS
     Tokyo
    0.54
     s
    0.54
     <
    0.52
    )
    0.51
     kitten
    0.50
     )
    0.49
     ex
    0.48
     ]
    0.48
     Perg
    0.48
     freshwater
    0.48
    Activations Density 0.001%

    No Known Activations