© 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. 34-GEMMASCOPE-RES-131K
    4. 115653
    Prev
    Next
    INDEX
    Explanations

    penetration of armor

    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
    Cevap
    -0.90
    ();)
    -0.77
    attrs
    -0.77
    ★★★★★
    -0.75
     Friday
    -0.74
     Sä
    -0.74
     Jimmy
    -0.73
    Açık
    -0.73
     ven
    -0.73
    చు
    -0.73
    POSITIVE LOGITS
     armor
    1.91
     armour
    1.66
    Armor
    1.31
     Armor
    1.25
     armored
    1.22
    装甲
    1.19
    armor
    1.19
     Armour
    1.17
     armoured
    1.16
     plates
    1.04
    Activations Density 0.014%

    No Known Activations