© 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. 52697
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
     a
    0.58
     after
    0.58
    )$
    0.54
    )\
    0.52
     and
    0.51
    [/
    0.51
    ),
    0.50
     после
    0.50
     when
    0.49
     P
    0.47
    POSITIVE LOGITS
    cheidung
    0.53
     dukkham
    0.51
     İst
    0.50
    ভৃতি
    0.47
     podej
    0.46
    съ
    0.45
     unbear
    0.45
    ய்டா
    0.44
     semelh
    0.43
     జగ
    0.43
    Activations Density 0.011%

    No Known Activations