© 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. 47877
    Prev
    Next
    INDEX
    Explanations

    opinion filed November

    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
    propan
    -0.82
     Fuzz
    -0.76
     diffusivity
    -0.72
    wah
    -0.70
     ceasefire
    -0.69
    Pepper
    -0.69
    pillar
    -0.69
    満足
    -0.68
    hülle
    -0.68
     slowdown
    -0.67
    POSITIVE LOGITS
    gment
    0.68
    赦
    0.65
     Schaefer
    0.63
     му
    0.63
    navigationItem
    0.59
    シェ
    0.59
     Schäfer
    0.59
     Electronics
    0.59
    itio
    0.59
    posure
    0.58
    Activations Density 0.098%

    No Known Activations