© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 227547
    Prev
    Next
    INDEX
    Explanations

    future possibilities or definitions

    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
    d
    0.51
    co
    0.50
    OHC
    0.48
     stare
    0.48
     Pluto
    0.48
     whine
    0.47
    灶
    0.47
     Cohen
    0.47
    er
    0.47
     l
    0.46
    POSITIVE LOGITS
     berbeda
    0.55
    ではない
    0.52
    比べて
    0.51
     例えば
    0.47
     unterschiedlich
    0.46
     Sebagai
    0.46
    Puede
    0.45
     diferite
    0.45
     ίδ
    0.45
    重要な
    0.45
    Activations Density 0.000%

    No Known Activations