© 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. 34657
    Prev
    Next
    INDEX
    Explanations

    building a plot

    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
     Describes
    0.50
     दिग्गज
    0.50
    ه
    0.50
    FRANK
    0.49
    鲔
    0.49
    These
    0.49
    ун
    0.48
    Τα
    0.46
     他们
    0.46
    Mature
    0.46
    POSITIVE LOGITS
     a
    0.53
    asse
    0.51
    iga
    0.50
    issa
    0.48
    rov
    0.48
    eric
    0.47
    ique
    0.47
    esa
    0.47
     Nar
    0.46
    ès
    0.46
    Activations Density 0.001%

    No Known Activations