© 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. 12098
    Prev
    Next
    INDEX
    Explanations

    home server and cloud

    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
     demonstrate
    0.43
    尭
    0.41
     ć
    0.39
     Vogue
    0.38
    oxygen
    0.37
     супра
    0.37
     Ib
    0.36
     lccn
    0.36
     Demonstrate
    0.36
    徂
    0.36
    POSITIVE LOGITS
    Docker
    0.63
    docker
    0.58
     NAS
    0.51
     docker
    0.51
    hass
    0.50
    NAS
    0.49
    SMB
    0.49
     SMB
    0.49
     Plex
    0.48
    nas
    0.47
    Activations Density 0.139%

    No Known Activations