© 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-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 3663
    Prev
    Next
    INDEX
    Explanations

    attack and damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     longitude
    1.11
     melon
    1.04
    향
    1.03
     parametr
    1.00
     Boardwalk
    0.98
    ometric
    0.97
    sciutto
    0.96
     Conley
    0.96
    OGLE
    0.96
    桡
    0.95
    POSITIVE LOGITS
     attackers
    1.67
    attacking
    1.64
    attack
    1.58
    受伤
    1.57
    Destroy
    1.55
    Attack
    1.52
     hazır
    1.50
     آماده
    1.50
    chunks
    1.47
     attacker
    1.46
    Activations Density 0.182%

    No Known Activations