© 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. 49729
    Prev
    Next
    INDEX
    Explanations

    myths about life and destruction

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

    die

    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
     potencialmente
    0.46
     рам
    0.46
     infrastructural
    0.45
    歉
    0.44
     CoA
    0.43
     контек
    0.42
     BSTC
    0.41
     deacetyl
    0.41
    嬌
    0.41
    CoA
    0.41
    POSITIVE LOGITS
    ंजनों
    0.46
    rétaire
    0.41
     Tallinn
    0.40
    ハウス
    0.39
     selfishness
    0.39
     কষ্টের
    0.39
    encoder
    0.39
     ৃ
    0.39
     ചെറിയ
    0.39
    áne
    0.39
    Activations Density 0.003%

    No Known Activations