© 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. 71129
    Prev
    Next
    INDEX
    Explanations

    species, certain other words

    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
     Am
    0.48
    é
    0.46
     Ag
    0.46
    ic
    0.46
     Ic
    0.45
     Pe
    0.44
     for
    0.44
     Nie
    0.43
     Caval
    0.43
     TE
    0.43
    POSITIVE LOGITS
    噱
    0.46
    Certain
    0.46
    mr
    0.46
    Department
    0.45
    キレイ
    0.45
    Special
    0.44
    וא
    0.44
    Prz
    0.44
    Singapore
    0.43
    Dequeue
    0.43
    Activations Density 0.001%

    No Known Activations