© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102218
    Prev
    Next
    INDEX
    Explanations

    adding or appending code

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

    method calls that chain or add elements, particularly `.concat()` and `.append()` in programming 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
     enlever
    -1.37
    ୌ
    -1.32
     الرغم
    -1.30
     samme
    -1.29
     miró
    -1.23
     храм
    -1.21
    鸷
    -1.20
     tylko
    -1.18
     حتی
    -1.16
    isan
    -1.15
    POSITIVE LOGITS
     they
    1.85
     of
    1.68
    Seems
    1.66
    This
    1.49
     этим
    1.45
    says
    1.38
     Bewußt
    1.38
     Commencez
    1.37
    More
    1.37
     part
    1.37
    Activations Density 0.001%

    No Known Activations