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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17012
    Prev
    Next
    INDEX
    Explanations

    classic and contrast

    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
    מה
    0.48
    ➷
    0.46
    抓住
    0.45
    =
    0.44
    ashore
    0.44
    reathe
    0.44
     ਕਰਨ
    0.44
    emo
    0.44
    Wak
    0.44
    At
    0.43
    POSITIVE LOGITS
     работ
    0.43
    рган
    0.42
     свои
    0.42
     অর্থে
    0.41
     Xinjiang
    0.41
     LHC
    0.40
     Southeastern
    0.40
    俅
    0.39
     Diana
    0.39
     warrant
    0.39
    Activations Density 0.000%

    No Known Activations