© 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. 19037
    Prev
    Next
    INDEX
    Explanations

    , on, two

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

    false premises and beliefs

    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
    id
    0.48
    áf
    0.45
    ema
    0.45
    lä
    0.44
    <!--
    0.44
    version
    0.44
    vida
    0.44
    {
    0.43
    uč
    0.42
    ónde
    0.42
    POSITIVE LOGITS
     среднего
    0.45
     lien
    0.44
    দানি
    0.43
     Presentation
    0.43
     Disabilities
    0.42
    ่อย
    0.42
     прадстаў
    0.42
     presentation
    0.41
     deprivation
    0.41
     situational
    0.41
    Activations Density 0.000%

    No Known Activations