© 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. 35037
    Prev
    Next
    INDEX
    Explanations

    various list terminators or separators

    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
    ierzchn
    0.49
    ške
    0.47
     Спорттук
    0.46
     Дні
    0.46
    ຜ
    0.46
     유
    0.46
    áneas
    0.46
    <unused722>
    0.45
    tochy
    0.45
    icznego
    0.45
    POSITIVE LOGITS
     वाकई
    0.44
     difference
    0.43
     truly
    0.43
     degree
    0.42
     bloc
    0.42
     incredible
    0.41
    degree
    0.41
     true
    0.41
     Difference
    0.41
     democr
    0.40
    Activations Density 0.002%

    No Known Activations