© 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-65K
    7. 4331
    Prev
    Next
    INDEX
    Explanations

    both, multiple, several, combined

    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_65k_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
    ייתה
    0.46
    ፐ
    0.40
    Argent
    0.39
    Че
    0.39
    Respiratory
    0.39
    實際上
    0.39
    鼓
    0.39
    ผม
    0.39
    вершен
    0.39
    植
    0.39
    POSITIVE LOGITS
     both
    0.63
     multiple
    0.54
     flere
    0.52
     Both
    0.50
     sowohl
    0.50
     several
    0.49
     både
    0.49
     combined
    0.49
    both
    0.48
     mehrere
    0.47
    Activations Density 0.065%

    No Known Activations