© 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. 179154
    Prev
    Next
    INDEX
    Explanations

    therapy, increase, authority, farm

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

    purpose, tolerance, everything

    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
     même
    0.53
     गोप
    0.49
     GoObject
    0.48
     ısı
    0.48
     janë
    0.47
    ⚉
    0.47
     μπορεί
    0.47
     naszym
    0.47
     telewiz
    0.47
    मिटेड
    0.46
    POSITIVE LOGITS
    n
    0.49
    single
    0.48
    Mill
    0.47
    sam
    0.45
    Single
    0.45
    0
    0.45
    Level
    0.45
    C
    0.45
    Hast
    0.44
    dumps
    0.44
    Activations Density 0.001%

    No Known Activations