© 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. 77968
    Prev
    Next
    INDEX
    Explanations

    Exhaustion, abuse, translator

    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
     K
    0.57
    ში
    0.54
     Dig
    0.50
     Par
    0.49
     Samuels
    0.49
     Ka
    0.47
     Parrot
    0.47
     Laure
    0.47
     Wild
    0.47
     The
    0.46
    POSITIVE LOGITS
     २०
    0.46
    ِی
    0.46
     बल्ले
    0.44
     पुढील
    0.44
     потери
    0.43
    鴨
    0.43
     handover
    0.43
    clientsdetails
    0.42
     vacate
    0.42
    uerpo
    0.41
    Activations Density 0.001%

    No Known Activations