© 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. 199493
    Prev
    Next
    INDEX
    Explanations

    why and then

    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
    హ
    0.50
     colonies
    0.44
    很多
    0.44
     huts
    0.44
    数组
    0.44
     bars
    0.43
    વ
    0.43
    गणना
    0.42
    ম
    0.42
    式
    0.42
    POSITIVE LOGITS
    trust
    0.46
    tumor
    0.46
     เต็ม
    0.46
    oció
    0.46
    disease
    0.46
    sufficient
    0.46
    цій
    0.45
    coding
    0.45
    coord
    0.44
    ́t
    0.44
    Activations Density 0.003%

    No Known Activations