© 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-65K
    7. 65051
    Prev
    Next
    INDEX
    Explanations

    document everything

    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_65k_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
     riforma
    0.49
     Nú
    0.45
     réforme
    0.44
    ヨーロッパ
    0.44
    Sehr
    0.44
     شکست
    0.44
    艨
    0.44
    ೇಯ
    0.43
     ruchu
    0.43
    hacking
    0.43
    POSITIVE LOGITS
     اپ
    0.53
     v
    0.50
     explicit
    0.50
    ough
    0.49
    endar
    0.48
     operation
    0.47
    ck
    0.47
     k
    0.46
     disk
    0.46
    ucked
    0.46
    Activations Density 0.003%

    No Known Activations