© 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. 222620
    Prev
    Next
    INDEX
    Explanations

    sequences following common prepositions

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

    key changes made

    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
    엷
    0.49
    дів
    0.47
     ৮
    0.44
    Didn
    0.43
    뉸
    0.43
    सादर
    0.42
    钱
    0.42
    幼儿
    0.42
    তবু
    0.42
    둴
    0.42
    POSITIVE LOGITS
     haci
    0.51
     expedite
    0.48
     mastermind
    0.48
     denounce
    0.47
     de
    0.47
     could
    0.47
     master
    0.46
     останови
    0.45
     exhausting
    0.45
     reporter
    0.45
    Activations Density 0.001%

    No Known Activations