© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 77975
    Prev
    Next
    INDEX
    Explanations

    another or again

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

    bolded text or lists

    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
    Negative Logits
    Spo
    0.40
    ☟
    0.39
    льны
    0.38
    Hell
    0.38
    โพ
    0.38
    ਲਾ
    0.37
     всем
    0.37
    Bullets
    0.36
    Voids
    0.36
    給
    0.36
    POSITIVE LOGITS
     another
    0.43
     again
    0.40
     Thirdly
    0.40
     ANOTHER
    0.39
    again
    0.38
     AGAIN
    0.37
     Another
    0.36
     nữa
    0.34
     Nusa
    0.34
     extensively
    0.34
    Activations Density 0.047%

    No Known Activations