Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 4777
    Prev
    Next
    INDEX
    Explanations

    You are right indeed

    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
    =?
    0.39
     bonheur
    0.39
     Просто
    0.38
     helst
    0.38
    ASSI
    0.37
    とにかく
    0.37
    =?,
    0.35
     radiator
    0.35
    ??
    0.34
    <?=$
    0.34
    POSITIVE LOGITS
     indeed
    1.59
    确实
    1.41
    確かに
    1.40
     Indeed
    1.36
    Indeed
    1.32
    確實
    1.32
    indeed
    1.27
     đúng
    1.17
    的确
    1.14
     effectivement
    1.13
    Activations Density 0.038%

    No Known Activations