© 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. 34-GEMMASCOPE-RES-131K
    7. 83647
    Prev
    Next
    INDEX
    Explanations

    length and its variants

    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
    caneca
    -1.00
    盞
    -0.99
    榀
    -0.98
    Geografie
    -0.96
    滁
    -0.96
    茘
    -0.94
    ﮑ
    -0.92
     responsibly
    -0.91
    Manganese
    -0.91
    ぢ
    -0.90
    POSITIVE LOGITS
     Length
    1.43
    length
    1.40
    ier
    1.36
    ening
    1.27
    ened
    1.18
    ());
    1.17
    setLength
    1.16
    Length
    1.13
     of
    1.11
     Learn
    1.09
    Activations Density 0.021%

    No Known Activations