© 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. 31-GEMMASCOPE-2-RES-262K
    7. 22531
    Prev
    Next
    INDEX
    Explanations

    comparative or contrastive conjunctions

    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_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
     (
    0.39
    ual
    0.39
    OL
    0.39
    Love
    0.38
    icious
    0.38
    ny
    0.38
    cmd
    0.37
    I
    0.37
     motivating
    0.37
    E
    0.37
    POSITIVE LOGITS
     لكن
    0.47
     lekin
    0.47
     porém
    0.46
    𒆪
    0.46
     Porém
    0.44
     relatives
    0.44
     ゆっくり
    0.43
     cependant
    0.43
     corrects
    0.43
    прочем
    0.43
    Activations Density 0.007%

    No Known Activations