© 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. 75471
    Prev
    Next
    INDEX
    Explanations

    "home" contexts

    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
     explosive
    -0.74
     épouse
    -0.72
     Complex
    -0.69
     GPs
    -0.66
     Todd
    -0.65
     structure
    -0.65
    サギ
    -0.63
    POA
    -0.63
     berarti
    -0.63
    ꯩ
    -0.63
    POSITIVE LOGITS
     counties
    1.11
     Counties
    1.09
     truths
    1.06
     comforts
    0.94
     tapas
    0.85
     county
    0.84
    truth
    0.82
    pasar
    0.81
    Captain
    0.80
     museo
    0.76
    Activations Density 0.022%

    No Known Activations