© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108930
    Prev
    Next
    INDEX
    Explanations

    adding a mask or layer

    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
    }]=
    0.47
    तर
    0.43
    تر
    0.42
    陈
    0.41
     Xian
    0.41
     صنعت
    0.41
    بر
    0.40
    uter
    0.39
    文章
    0.39
    时
    0.39
    POSITIVE LOGITS
    Js
    0.54
     +/-
    0.50
     promulgating
    0.50
     immunohist
    0.49
     modulates
    0.48
     Į
    0.48
     category
    0.47
    āta
    0.47
     pathologic
    0.45
     зав
    0.45
    Activations Density 0.002%

    No Known Activations