© 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. 61861
    Prev
    Next
    INDEX
    Explanations

    The LORD presents

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

    AntiGPT contrast

    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
     jurisprudence
    0.50
     declarative
    0.48
     ventil
    0.47
     integrand
    0.47
     deprecated
    0.47
     একখানি
    0.47
    嶈
    0.46
     সংস্ক
    0.46
     mindfulness
    0.45
     ṣ
    0.45
    POSITIVE LOGITS
    -
    0.48
    n
    0.46
    NOTICE
    0.45
    at
    0.44
    with
    0.44
     खतरा
    0.44
    TT
    0.44
    ff
    0.43
    DB
    0.43
    ان
    0.43
    Activations Density 0.000%

    No Known Activations