© 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. 3785
    Prev
    Next
    INDEX
    Explanations

    slightly modified versions

    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
     injections
    0.47
     restarts
    0.46
     problems
    0.45
     hear
    0.45
     mines
    0.45
     integrating
    0.45
     tine
    0.45
    #'
    0.45
     why
    0.44
     pipelines
    0.44
    POSITIVE LOGITS
    osi
    0.57
    en
    0.49
     لهذه
    0.48
    ando
    0.47
     Beit
    0.47
     использова
    0.46
     फुलकारी
    0.46
     Seth
    0.45
    ita
    0.45
     Seph
    0.45
    Activations Density 0.005%

    No Known Activations