© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 195376
    Prev
    Next
    INDEX
    Explanations

    #hashtag and expand

    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_40_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
     ყველა
    0.38
     jednog
    0.38
     ovog
    0.37
    oha
    0.37
    弃
    0.37
     चाहि
    0.37
     ಬಂಧ
    0.37
    必要
    0.36
     dovoljno
    0.36
     সংগ্রহের
    0.36
    POSITIVE LOGITS
    だけの
    0.39
     headset
    0.38
    ^{-}\
    0.38
    只
    0.38
     gewoon
    0.38
    つまり
    0.37
    hel
    0.36
     just
    0.36
    helia
    0.36
     vaan
    0.36
    Activations Density 0.000%

    No Known Activations