© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 121630
    Prev
    Next
    INDEX
    Explanations

    pretend or supposed

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

    pretending or simulating something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    a
    0.53
    ̟
    0.47
     отлич
    0.47
     склон
    0.44
    ه
    0.43
     doth
    0.43
     බැ
    0.43
     a
    0.42
     dishonest
    0.42
     более
    0.42
    POSITIVE LOGITS
     supposed
    0.66
     pretended
    0.64
     supposedly
    0.61
    pret
    0.59
    所谓的
    0.58
     pretends
    0.56
     pretend
    0.55
     Pret
    0.55
     pret
    0.53
    pseudo
    0.52
    Activations Density 0.104%

    No Known Activations