© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7079
    Prev
    Next
    INDEX
    Explanations

    "I am" or "I'm" statements

    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_12_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
     рә
    1.13
     ini
    1.05
     this
    1.03
    ңыз
    0.99
    ∑</
    0.96
     перво
    0.94
    一提
    0.92
     Prior
    0.92
     **
    0.90
     Hose
    0.88
    POSITIVE LOGITS
    elum
    1.72
    varage
    1.64
    živ
    1.62
    ffield
    1.62
    ーブ
    1.60
    fordshire
    1.60
    ŕ
    1.59
    atism
    1.59
    nonzero
    1.58
     kmeans
    1.57
    Activations Density 0.138%

    No Known Activations