© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1134
    Prev
    Next
    INDEX
    Explanations

    code delimiters and keywords

    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
    ăm
    -0.90
    proceso
    -0.81
     Unterstüt
    -0.81
     over
    -0.80
    油
    -0.75
     Kontroll
    -0.75
    ㅎ
    -0.75
     Hood
    -0.73
     j
    -0.73
     from
    -0.72
    POSITIVE LOGITS
    ↵
    0.96
     ''}
    0.93
     ""}
    0.91
    ほん
    0.88
    谢谢你
    0.83
     shreds
    0.83
    ."]
    0.80
     sapphire
    0.80
    \}
    0.79
    ︡
    0.79
    Activations Density 0.000%

    No Known Activations