© 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-16K
    7. 9282
    Prev
    Next
    INDEX
    Explanations

    between, mutual, pairing, comparison

    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_16k_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
     Jord
    0.45
    诌
    0.44
    箬
    0.42
     mantenimiento
    0.41
     grabación
    0.41
     Laufe
    0.41
     शी
    0.40
     Gesicht
    0.40
    ு
    0.40
    竻
    0.40
    POSITIVE LOGITS
     mutual
    0.94
     between
    0.90
    同士
    0.88
     pairing
    0.87
     між
    0.85
     comparing
    0.84
     merging
    0.83
     между
    0.81
    Between
    0.81
    相互
    0.81
    Activations Density 1.238%

    No Known Activations