© 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. 187625
    Prev
    Next
    INDEX
    Explanations

    standard 'er own one

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

    simplifying or representing concepts

    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
    ไหม
    0.47
    !
    0.46
     پڑ
    0.46
    tare
    0.44
     labelling
    0.44
     হারানোর
    0.43
     glor
    0.43
     shuffling
    0.42
    거운
    0.42
     crying
    0.41
    POSITIVE LOGITS
    <0x80>
    0.71
    лла
    0.51
    反応
    0.49
     posición
    0.48
     músicos
    0.47
    ʀ
    0.47
    ноу
    0.46
     дослід
    0.46
    bouw
    0.46
     materiál
    0.45
    Activations Density 0.000%

    No Known Activations