© 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. 108463
    Prev
    Next
    INDEX
    Explanations

    eager to

    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
     manu
    0.53
     crede
    0.52
     manual
    0.52
    ।
    0.51
     code
    0.51
     potencia
    0.51
     cib
    0.51
     in
    0.50
     continuously
    0.50
     nome
    0.49
    POSITIVE LOGITS
     आदित्यनाथ
    0.49
     художника
    0.46
    দায়িক
    0.46
     underwhelming
    0.45
    丰富
    0.44
    倌
    0.44
     формата
    0.44
    ohms
    0.43
    ≋
    0.43
     =&
    0.43
    Activations Density 0.001%

    No Known Activations