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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113839
    Prev
    Next
    INDEX
    Explanations

    Objective-C code constructs

    np_acts-logits-general · gemini-2.5-flash-lite

    underscores that are part of variable or identifier names in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ዡ
    -2.28
    ྵ
    -2.25
    哢
    -2.16
    Of
    -2.13
    鹋
    -2.06
    一百
    -2.02
    .’
    -2.00
    erweise
    -1.99
    a
    -1.96
     نکنید
    -1.93
    POSITIVE LOGITS
     —
    2.56
    ся
    2.53
    л
    2.45
    AutoresizingMask
    2.44
     \&
    2.42
     "
    2.38
     (!__
    2.34
    ?"
    2.34
    ↵
    2.16
    ли
    2.14
    Activations Density 0.007%

    No Known Activations