© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67679
    Prev
    Next
    INDEX
    Explanations

    code structure and logic

    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_22/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
    ㅐ
    -1.21
    dding
    -1.17
    jiet
    -1.15
     lanterna
    -1.13
     sapatos
    -1.10
    饪
    -1.09
    bcrypt
    -1.08
     coussin
    -1.06
    ỡng
    -1.05
    cted
    -1.05
    POSITIVE LOGITS
     their
    1.07
     because
    1.05
     when
    1.05
     had
    1.01
     by
    0.98
     if
    0.96
    if
    0.94
     almost
    0.91
     told
    0.91
     they
    0.89
    Activations Density 0.009%

    No Known Activations