© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7357
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases following nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )="
    0.41
    accomp
    0.41
     فیصلے
    0.40
    所以我
    0.40
    Donc
    0.40
    論文
    0.40
     kèm
    0.39
    밉
    0.39
    確認
    0.39
    tional
    0.39
    POSITIVE LOGITS
    O
    0.43
    U
    0.42
     partido
    0.41
     dich
    0.38
    H
    0.38
     vezes
    0.38
    О
    0.38
     ਆ
    0.37
     polic
    0.37
     cavity
    0.37
    Activations Density 0.000%

    No Known Activations