© 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. 22-GEMMASCOPE-RES-131K
    4. 68724
    Prev
    Next
    INDEX
    Explanations

    If the

    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_22/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
     also
    -1.41
     también
    -1.30
     также
    -1.14
     também
    -1.09
     тоже
    -1.05
     kvinnor
    -1.05
    AllowUser
    -1.04
     stadion
    -1.02
    来ました
    -1.01
    "",
    
    -1.00
    POSITIVE LOGITS
     you
    1.72
     if
    1.48
    既然
    1.13
     now
    1.09
    if
    1.09
     mittlerweile
    1.09
    如果你
    1.08
     we
    1.08
     since
    1.05
     inzwischen
    1.04
    Activations Density 0.012%

    No Known Activations