© 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. 150869
    Prev
    Next
    INDEX
    Explanations

    returned goods with address

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

    why, Not

    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
     Pena
    0.58
    \
    0.54
     formas
    0.54
    l
    0.54
    ían
    0.53
     codons
    0.50
    Sos
    0.48
    ล
    0.48
     Sos
    0.47
     पूर्ण
    0.47
    POSITIVE LOGITS
    pperware
    0.45
     mentoring
    0.43
    했다고
    0.43
     iniziato
    0.43
    പ്പിച്ചി
    0.43
     giường
    0.42
    ርዓ
    0.41
     zei
    0.41
    しており
    0.41
     annivers
    0.41
    Activations Density 0.001%

    No Known Activations