© 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. 54077
    Prev
    Next
    INDEX
    Explanations

    citation numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    +'/
    -1.04
    ῴ
    -0.97
    》(
    -0.97
     около
    -0.96
     eines
    -0.94
    帖最后由
    -0.92
     meski
    -0.92
    非常好
    -0.91
    شكرا
    -0.91
    に行って
    -0.91
    POSITIVE LOGITS
    )
    0.94
     stated
    0.94
    research
    0.93
     research
    0.91
     \&
    0.90
     cited
    0.88
    paravant
    0.85
     &
    0.85
    ).
    0.85
     citi
    0.84
    Activations Density 0.015%

    No Known Activations