© 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. 75048
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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
    strated
    -1.02
     pengar
    -1.02
     intelligente
    -0.99
    owski
    -0.97
    žnost
    -0.96
     pertinente
    -0.95
    を含
    -0.95
    を
    -0.92
    ":"",
    -0.92
    tacular
    -0.92
    POSITIVE LOGITS
     μόνο
    1.14
     only
    1.07
     sintió
    1.06
    Only
    1.02
     pihaknya
    1.01
     Mère
    1.00
    edero
    1.00
     והוא
    0.97
     Kühlschrank
    0.97
    rimos
    0.96
    Activations Density 0.005%

    No Known Activations