© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179671
    Prev
    Next
    INDEX
    Explanations

    children there, flashing needs

    np_acts-logits-general · gemini-2.5-flash-lite

    analysts and variable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ev
    0.53
    ar
    0.53
    ie
    0.51
    one
    0.51
    ica
    0.51
    ↵
    0.49
    Brazil
    0.48
    ik
    0.48
    then
    0.48
    <%
    0.48
    POSITIVE LOGITS
     transg
    0.44
     inning
    0.43
     slurry
    0.42
     olmadığını
    0.41
     sket
    0.40
     cuestion
    0.40
     fréquemment
    0.40
     obser
    0.40
     stries
    0.40
     oligonucle
    0.39
    Activations Density 0.001%

    No Known Activations