© 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. 40779
    Prev
    Next
    INDEX
    Explanations

    by criterion

    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
     একদিন
    0.42
     ferries
    0.40
     future
    0.39
     প্রতিনিধ
    0.38
     reductions
    0.38
     an
    0.37
     Adidas
    0.37
    、
    0.36
    andex
    0.36
    AVES
    0.36
    POSITIVE LOGITS
     그러니까
    0.54
    ней
    0.48
    روں
    0.45
    тят
    0.44
    तना
    0.43
    immobil
    0.43
    eux
    0.42
    к
    0.42
    зывают
    0.41
    пят
    0.41
    Activations Density 0.001%

    No Known Activations