© 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. 76525
    Prev
    Next
    INDEX
    Explanations

    links to maps

    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
     Chines
    0.48
     Confucian
    0.46
     bourgeoisie
    0.45
     Alexander
    0.43
     Qing
    0.43
    晌
    0.43
     Ethiopian
    0.42
    followfollow
    0.42
     Eternal
    0.42
     svoje
    0.41
    POSITIVE LOGITS
    ti
    0.46
    ников
    0.44
     ઘટ
    0.44
    频
    0.42
    UD
    0.41
    tan
    0.41
     neuropathy
    0.40
    <0xB0>
    0.40
    ran
    0.39
     ανα
    0.39
    Activations Density 0.001%

    No Known Activations