© 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. 51369
    Prev
    Next
    INDEX
    Explanations

    authentic is

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

    authentic writing

    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
    ină
    0.44
     अफेयर्स
    0.43
    ÍN
    0.42
    弜
    0.42
    ત્મક
    0.42
    iovas
    0.42
     tři
    0.40
    চিত
    0.40
    ื้น
    0.40
     ফেলেছেন
    0.40
    POSITIVE LOGITS
    Authent
    0.53
    authentic
    0.50
    Semi
    0.47
    authent
    0.47
     authentic
    0.46
     Authentic
    0.46
    Start
    0.46
    Droid
    0.46
    V
    0.46
    RIG
    0.45
    Activations Density 0.000%

    No Known Activations