© 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. 153291
    Prev
    Next
    INDEX
    Explanations

    indemnification, kalkwasser, colony

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

    strategies involving parents

    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
    ен
    0.51
    ERRORTYPE
    0.50
     gemeinsam
    0.50
     ښ
    0.50
     együtt
    0.49
     Gemeins
    0.48
     düşük
    0.47
    ynku
    0.47
    ScheduledAction
    0.47
    سٹم
    0.47
    POSITIVE LOGITS
     mangroves
    0.48
    תי
    0.47
     to
    0.47
    א
    0.46
    ia
    0.45
    আমাকে
    0.45
     a
    0.45
     ANYTHING
    0.45
     ramen
    0.44
     Casc
    0.43
    Activations Density 0.001%

    No Known Activations