© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10668
    Prev
    Next
    INDEX
    Explanations

    need is what is left

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    much
    0.43
    onym
    0.41
    力が
    0.41
    ➚
    0.40
    ноп
    0.40
    很大
    0.40
    [![
    0.39
    较大
    0.39
     much
    0.38
    ８
    0.38
    POSITIVE LOGITS
     restantes
    0.54
     remaining
    0.52
    剩下的
    0.51
    剩下
    0.50
     restante
    0.49
     Remaining
    0.43
     determines
    0.42
     অবশিষ্ট
    0.42
     final
    0.41
     adjourn
    0.41
    Activations Density 0.000%

    No Known Activations