© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 38667
    Prev
    Next
    INDEX
    Explanations

    summarizing, translating, and remembering tasks

    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
     கொண்டே
    0.46
    ಲ
    0.43
     используются
    0.42
     時
    0.40
     אבל
    0.40
     сами
    0.40
     comenc
    0.40
    時
    0.39
    ialmente
    0.39
    си
    0.38
    POSITIVE LOGITS
     sabbatical
    0.50
     epistem
    0.49
     liturgical
    0.48
     anest
    0.47
     idiosyncratic
    0.47
     apostolic
    0.47
     evidenced
    0.46
     mitig
    0.46
     shameful
    0.46
     Ereign
    0.46
    Activations Density 0.009%

    No Known Activations