© 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-262K
    7. 199809
    Prev
    Next
    INDEX
    Explanations

    explain the process

    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_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
     người
    0.55
     phone
    0.54
     para
    0.53
     ou
    0.52
     khu
    0.52
     {
    0.52
     see
    0.52
    Monday
    0.52
     tous
    0.50
     was
    0.50
    POSITIVE LOGITS
    ISTIC
    0.46
    θηκαν
    0.45
    sprach
    0.44
    сування
    0.44
     создания
    0.43
     adsorb
    0.43
     momentous
    0.43
    <unused347>
    0.43
     dilaksanakan
    0.42
    мого
    0.42
    Activations Density 0.001%

    No Known Activations