© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26945
    Prev
    Next
    INDEX
    Explanations

    teams competing or opposing

    np_acts-logits-general · gemini-2.5-flash-lite

    comparing models and products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     සහ
    0.42
    andfeel
    0.42
     ตัด
    0.41
     אי
    0.41
    intermedi
    0.40
    畱
    0.40
    诋
    0.39
    ܛ
    0.39
    ཌ
    0.39
    adece
    0.39
    POSITIVE LOGITS
     counterpart
    0.58
     counterparts
    0.56
     opponent
    0.49
     opposing
    0.45
     fellow
    0.44
     oncoming
    0.37
     opponents
    0.37
     Fellow
    0.36
     seasoned
    0.36
     countertop
    0.35
    Activations Density 0.254%

    No Known Activations