© 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. 102644
    Prev
    Next
    INDEX
    Explanations

    celebrity news and exclusives

    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
    sidenav
    -0.76
    ołnier
    -0.75
    ENCH
    -0.75
    ATHAN
    -0.74
     Cis
    -0.74
     הזה
    -0.73
    addEdge
    -0.72
    jskiej
    -0.72
     Stad
    -0.71
     Pec
    -0.71
    POSITIVE LOGITS
     ET
    1.33
    ET
    1.10
    ETER
    0.82
    TORE
    0.81
    EXCLUSIVE
    0.80
    et
    0.79
     bemerken
    0.77
     eyewitness
    0.74
     blacklist
    0.73
     EXCLUSIVE
    0.73
    Activations Density 0.012%

    No Known Activations