© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11373
    Prev
    Next
    INDEX
    Explanations

    recipe measurements and ingredients

    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_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
    st
    0.52
    a
    0.46
    t
    0.45
    bnb
    0.45
    o
    0.45
    rington
    0.45
    mild
    0.44
    stern
    0.44
     Mild
    0.44
    ه
    0.44
    POSITIVE LOGITS
     equação
    0.59
     xhrObj
    0.53
     diamètre
    0.52
     obtains
    0.50
     obtenue
    0.50
     socket
    0.50
     extremal
    0.50
     clockRadius
    0.50
     hexadecimal
    0.48
     phospholipids
    0.48
    Activations Density 0.006%

    No Known Activations