© 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-65K
    7. 65093
    Prev
    Next
    INDEX
    Explanations

    wood standing, time waiting, parseInt, image data

    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_65k_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
    ረው
    0.47
    ᱘
    0.44
    പ്പിച്ച
    0.43
    నాలు
    0.42
    ﻭ
    0.42
    츰
    0.42
    נן
    0.42
     ನಂತರ
    0.41
    אן
    0.41
    ᱐
    0.41
    POSITIVE LOGITS
     Kuro
    0.47
     Lin
    0.47
     Portrait
    0.44
     On
    0.43
     Ty
    0.43
     Aks
    0.43
     Eli
    0.42
    ovy
    0.42
     Kut
    0.42
     Kro
    0.41
    Activations Density 0.017%

    No Known Activations