© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8565
    Prev
    Next
    INDEX
    Explanations

    each, respectively, both

    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_16k_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
     знаходиться
    0.41
    焜
    0.41
     ಮತ್ತ
    0.40
    までに
    0.40
     နောက်
    0.39
     もう
    0.39
     находится
    0.38
     மூன்றாவது
    0.38
     ಇನ್ನ
    0.38
     ٿ
    0.38
    POSITIVE LOGITS
    それぞれ
    0.44
     surv
    0.37
     begge
    0.37
     entrambi
    0.36
     각각
    0.35
     ама
    0.34
     XVI
    0.34
    żliw
    0.34
     overseen
    0.34
     respectivement
    0.34
    Activations Density 0.350%

    No Known Activations