© 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. 34-GEMMASCOPE-RES-131K
    4. 90542
    Prev
    Next
    INDEX
    Explanations

    scientific contexts

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

    periods/full stops at the end of sentences in formal documents and transcripts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     and
    -1.36
     And
    -1.27
     krom
    -1.06
     варианты
    -1.05
    And
    -1.05
     INSTRUCTIONS
    -0.99
     soigneusement
    -0.96
    íe
    -0.96
    而
    -0.95
    Ŷ
    -0.94
    POSITIVE LOGITS
     that
    1.99
     we
    1.45
     it
    1.45
     I
    1.38
     as
    1.33
     may
    1.33
     Mungkin
    1.16
     Terkait
    1.15
     there
    1.14
     podrán
    1.13
    Activations Density 0.002%

    No Known Activations