© 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. 31556
    Prev
    Next
    INDEX
    Explanations

    snow conditions

    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
     Barbar
    -0.82
    ΤΟ
    -0.79
    paj
    -0.77
    sities
    -0.76
     rheumatic
    -0.75
    Disability
    -0.74
    freude
    -0.74
    notin
    -0.74
    verte
    -0.73
    eacute
    -0.73
    POSITIVE LOGITS
     consolidated
    1.09
     consolidate
    1.07
     consolidation
    0.99
     conditions
    0.95
     crust
    0.92
     consolidating
    0.89
     fir
    0.88
     firm
    0.88
     harden
    0.86
     primo
    0.84
    Activations Density 0.013%

    No Known Activations