© 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. 44909
    Prev
    Next
    INDEX
    Explanations

    like / as

    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
     Antique
    0.39
     タイヤ
    0.39
    ls
    0.38
     (!)
    0.38
    焉
    0.38
    ennial
    0.37
     맥
    0.37
     modernes
    0.36
    ნდა
    0.36
     Moderne
    0.36
    POSITIVE LOGITS
     like
    1.34
     seperti
    1.21
     kuten
    1.21
     כמו
    1.14
     مثل
    1.13
    如
    1.11
    Like
    1.09
     Like
    1.08
     مانند
    1.07
     như
    1.06
    Activations Density 0.128%

    No Known Activations