© 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. 74765
    Prev
    Next
    INDEX
    Explanations

    after leader or lying

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

    noodle races, doubt, birth year, honesty

    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
    isa
    0.54
    .
    0.46
    왈
    0.44
     કરવો
    0.44
    ess
    0.43
    oman
    0.42
    ës
    0.41
    iség
    0.41
    ette
    0.40
     ایل
    0.40
    POSITIVE LOGITS
     stockings
    0.55
     Аль
    0.52
     unconditional
    0.51
     régionale
    0.50
     curly
    0.50
    <unused23>
    0.49
    о
    0.49
     cohorts
    0.49
     tampa
    0.49
     regionales
    0.48
    Activations Density 0.000%

    No Known Activations