© 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. 12099
    Prev
    Next
    INDEX
    Explanations

    document section or directory

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

    references to content located below the current text position, often in the form of instructions or directives pointing to information further down the page.

    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
    Sự
    -1.32
     pertama
    -1.31
     mengumumkan
    -1.29
    глежда
    -1.27
     fruto
    -1.25
     animados
    -1.25
    ዣ
    -1.23
    usado
    -1.23
     klick
    -1.22
     mostrare
    -1.21
    POSITIVE LOGITS
     and
    1.36
     who
    1.36
     each
    1.34
     every
    1.22
     that
    1.21
    性和
    1.20
     this
    1.20
    !
    1.16
     next
    1.11
     השאלה
    1.10
    Activations Density 0.115%

    No Known Activations