© 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. 57087
    Prev
    Next
    INDEX
    Explanations

    exploring or analyzing ranges

    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
     I
    0.51
     anti
    0.48
     earnest
    0.47
    I
    0.47
     drug
    0.46
    Ver
    0.45
    Cor
    0.45
    Young
    0.43
     prieš
    0.42
    S
    0.42
    POSITIVE LOGITS
     请求
    0.49
    合适的
    0.46
    しますが
    0.46
    즐
    0.46
     bỏ
    0.44
    浪费
    0.44
     isDisabled
    0.44
    কে
    0.43
    కు
    0.43
    機会
    0.43
    Activations Density 0.008%

    No Known Activations