© 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. 10668
    Prev
    Next
    INDEX
    Explanations

    need to know: final

    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
    onym
    0.42
    much
    0.41
    ➚
    0.39
    [![
    0.38
    ነ
    0.38
    ப்பழ
    0.37
    Nimbus
    0.37
    ８
    0.37
     much
    0.37
    Much
    0.36
    POSITIVE LOGITS
     remaining
    0.51
     restantes
    0.48
    剩下
    0.46
     restante
    0.45
    剩下的
    0.45
     factor
    0.42
     Remaining
    0.41
     অবশিষ্ট
    0.41
     final
    0.40
    剩余
    0.39
    Activations Density 0.002%

    No Known Activations