© 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. 13807
    Prev
    Next
    INDEX
    Explanations

    conditions starting with if

    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
     komfor
    -1.19
     برگزاری
    -1.13
     ideen
    -1.12
    ferien
    -1.12
     konsep
    -1.09
    Neden
    -1.06
     pétrole
    -1.04
    sproble
    -1.04
     saati
    -1.04
     eksklu
    -1.04
    POSITIVE LOGITS
     if
    1.83
    If
    1.42
     If
    1.29
     does
    1.17
    有可能
    1.12
     guineas
    1.10
     если
    1.09
     unless
    1.07
     This
    1.05
    ammer
    1.05
    Activations Density 0.030%

    No Known Activations