© 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. 28603
    Prev
    Next
    INDEX
    Explanations

    deprives, illegal, low cost

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

    crucial because LLMs sensitive

    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
     epidemiological
    0.48
     palate
    0.47
     tenacity
    0.47
     polymorphism
    0.47
    </h3>
    0.45
     microns
    0.45
     clinical
    0.44
     valence
    0.44
    isins
    0.44
     geopolitical
    0.44
    POSITIVE LOGITS
    ků
    0.51
    們
    0.48
    Công
    0.48
    佢
    0.46
     họ
    0.46
    それぞれ
    0.46
     bốn
    0.45
     companhia
    0.45
    nú
    0.45
     ترك
    0.42
    Activations Density 0.000%

    No Known Activations