© 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. 240508
    Prev
    Next
    INDEX
    Explanations

    URI, rights, general, elements, entrance

    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
    petit
    0.53
    ა
    0.53
    ών
    0.49
    นิด
    0.48
    ቡ
    0.48
     rédu
    0.46
    द्दी
    0.46
    elan
    0.46
    <0xB8>
    0.46
    iraju
    0.46
    POSITIVE LOGITS
     amistad
    0.46
    的概念
    0.45
     countrymen
    0.45
    =\
    0.44
     Weekly
    0.44
    ：
    0.44
     Justicia
    0.43
     friendship
    0.42
    的使用
    0.42
     الحكم
    0.42
    Activations Density 0.000%

    No Known Activations