© 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. 53-GEMMASCOPE-2-RES-262K
    7. 12384
    Prev
    Next
    INDEX
    Explanations

    how things taste

    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_53_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
     setCount
    0.41
    Lookup
    0.37
     FSC
    0.36
    㼛
    0.36
     Johnson
    0.36
     JOHNSON
    0.35
     संधि
    0.35
     Fees
    0.34
    Pension
    0.34
    <unused24>
    0.34
    POSITIVE LOGITS
     taste
    4.09
     Taste
    3.58
    Taste
    3.58
    taste
    3.53
     tastes
    3.50
     tasted
    3.25
     맛
    3.09
    味
    3.00
     вку
    2.97
    맛
    2.92
    Activations Density 0.089%

    No Known Activations