© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93010
    Prev
    Next
    INDEX
    Explanations

    filing documents

    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
    fieras
    -0.88
     hobbies
    -0.80
     proiz
    -0.80
     delusions
    -0.79
    Історія
    -0.76
    pium
    -0.75
    ASKET
    -0.75
    嗗
    -0.74
    obat
    -0.74
    没了
    -0.73
    POSITIVE LOGITS
     paperwork
    4.06
     papers
    2.84
     documents
    2.63
     documentation
    2.42
    documents
    2.02
     papeles
    1.92
    papers
    1.91
     paper
    1.91
    paper
    1.89
    Papers
    1.89
    Activations Density 0.029%

    No Known Activations