© 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. 113323
    Prev
    Next
    INDEX
    Explanations

    stage rockets

    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
     outils
    0.47
     sandpaper
    0.47
     algorithm
    0.46
     sakit
    0.46
    oui
    0.44
    m
    0.44
    겟
    0.44
     prompts
    0.43
     raids
    0.43
    ມ
    0.43
    POSITIVE LOGITS
    АО
    0.46
     نفسها
    0.46
     版
    0.46
    称为
    0.45
     之
    0.45
     ску
    0.45
     тү
    0.44
    を追加
    0.44
     असलेले
    0.44
     höch
    0.44
    Activations Density 0.004%

    No Known Activations