© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3620
    Prev
    Next
    INDEX
    Explanations

    people and their connections

    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_16_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
     edilmiş
    0.46
     eines
    0.46
    Α
    0.45
    ида
    0.44
     ລັບ
    0.43
    СР
    0.43
     hernia
    0.43
     paralysis
    0.43
     anyag
    0.42
     gemaakt
    0.42
    POSITIVE LOGITS
     influencers
    0.51
    ام
    0.49
     dignitaries
    0.49
     superheroes
    0.47
     who
    0.46
    re
    0.45
    ザー
    0.45
    데
    0.45
    friends
    0.45
    つい
    0.44
    Activations Density 0.621%

    No Known Activations