© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11307
    Prev
    Next
    INDEX
    Explanations

    fake or surrogate

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is highly responsive to personal‐reference words—especially first‐person pronouns and analogous kinship or self-referential terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     eğ
    0.74
    Projectile
    0.71
    Attack
    0.68
     meneg
    0.68
    Motivational
    0.67
    오
    0.67
    Histogram
    0.66
     motorcycl
    0.66
     sistemat
    0.65
    Weapon
    0.64
    POSITIVE LOGITS
     surrog
    0.98
     surrogate
    0.98
     Surrogate
    0.86
     transf
    0.84
     fraudulently
    0.82
    偽
    0.80
     अनजान
    0.77
     identities
    0.77
     transplantation
    0.77
     جعلی
    0.75
    Activations Density 1.710%

    No Known Activations