© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9387
    Prev
    Next
    INDEX
    Explanations

    versions, editions, and media re-releases

    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_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
     grosso
    0.45
     திறந்து
    0.41
     synchronous
    0.41
     Geschmack
    0.40
     stereotyp
    0.40
    xygen
    0.39
     жан
    0.39
    蜴
    0.39
    遒
    0.39
     rhyth
    0.38
    POSITIVE LOGITS
     remastered
    0.91
     remaster
    0.86
     DVD
    0.84
    DVD
    0.80
     editions
    0.75
     reprint
    0.72
     reissue
    0.72
     Blu
    0.71
     HD
    0.71
     dvd
    0.71
    Activations Density 0.176%

    No Known Activations