© 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. 47984
    Prev
    Next
    INDEX
    Explanations

    characteristics and differences

    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
    ob
    0.50
    Theorem
    0.46
    όν
    0.44
    ອນ
    0.43
    rid
    0.42
    exp
    0.42
    ỹ
    0.41
    OB
    0.41
    ável
    0.40
    necessary
    0.40
    POSITIVE LOGITS
     characteristics
    0.57
     differed
    0.54
     differs
    0.54
     Características
    0.51
     differences
    0.51
     características
    0.49
     показателей
    0.49
     особенностей
    0.48
     differ
    0.48
     Differ
    0.47
    Activations Density 0.075%

    No Known Activations