© 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. 107042
    Prev
    Next
    INDEX
    Explanations

    committed use discounts

    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
     lubricant
    0.62
     sable
    0.59
     lubricants
    0.58
     மலச்சிக்க
    0.58
     mucus
    0.56
     soapy
    0.51
     commutation
    0.50
    р
    0.50
     contaminant
    0.50
     sealant
    0.49
    POSITIVE LOGITS
     குறி
    0.61
     визнача
    0.58
     மேற்க
    0.55
     주장
    0.54
     میں
    0.53
    வுக
    0.53
    ção
    0.53
    影响力
    0.53
    ik
    0.52
    nk
    0.52
    Activations Density 0.000%

    No Known Activations