© 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. 202579
    Prev
    Next
    INDEX
    Explanations

    discipline, Miami, converted, challenge, solution, analyzing, visit

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

    technical or domain-specific terms

    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
     surpre
    0.49
    δρο
    0.47
     subsequ
    0.47
    "><?
    0.46
    піль
    0.44
    ديد
    0.44
     تلك
    0.44
    出産
    0.42
     জন্মদিন
    0.41
     জন্মের
    0.40
    POSITIVE LOGITS
     Remington
    0.50
    Vh
    0.45
     Mehr
    0.44
    ndor
    0.44
     शिल्
    0.43
     作为
    0.43
    usr
    0.43
    Jag
    0.43
    ↵↵
    0.42
    tes
    0.42
    Activations Density 0.000%

    No Known Activations