© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118467
    Prev
    Next
    INDEX
    Explanations

    running deep

    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
    Interv
    -0.84
    あるいは
    -0.81
     interdependence
    -0.79
    usaha
    -0.76
    Raphael
    -0.75
    mesi
    -0.74
    central
    -0.73
    OfThe
    -0.73
    Screenshots
    -0.71
    hita
    -0.71
    POSITIVE LOGITS
     ١
    0.85
     wers
    0.77
    ắt
    0.77
    Ⓘ
    0.76
    Gat
    0.75
    古老
    0.73
    martre
    0.73
     kako
    0.72
    zom
    0.71
     synthase
    0.71
    Activations Density 0.061%

    No Known Activations