© 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. 122570
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

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

    contrast and qualification

    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
    0.49
     choisissez
    0.48
    बॉ
    0.47
    存于互联网档案馆
    0.46
     باندې
    0.46
    এর
    0.46
    䀓
    0.46
    的手
    0.45
     odmah
    0.44
    廾
    0.44
    POSITIVE LOGITS
     fragile
    0.54
     very
    0.51
     «
    0.48
     unscrupulous
    0.48
     trimethyl
    0.46
    ns
    0.46
     isset
    0.46
    uting
    0.46
     question
    0.46
    ute
    0.46
    Activations Density 0.001%

    No Known Activations