© 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. 194323
    Prev
    Next
    INDEX
    Explanations

    Disability Insurance

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

    capture, research, reject, divides

    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
     erwartet
    0.49
    BorderSize
    0.46
    Indexes
    0.46
     первую
    0.46
     ফলা
    0.45
    وء
    0.45
     overr
    0.45
    帔
    0.45
     ignores
    0.44
     газа
    0.44
    POSITIVE LOGITS
    asthenia
    0.52
    ductor
    0.51
    ſs
    0.47
    antra
    0.45
    ्च
    0.44
    curities
    0.44
    rania
    0.44
     देखना
    0.42
     priceless
    0.42
    ོ
    0.42
    Activations Density 0.000%

    No Known Activations