© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7982
    Prev
    Next
    INDEX
    Explanations

    code terminators or delimiters

    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
     بسم
    0.43
    шкина
    0.42
     trúc
    0.40
     hiçbir
    0.40
    ública
    0.39
    Solved
    0.39
    缟
    0.39
    prendre
    0.38
     никаких
    0.38
    руппа
    0.37
    POSITIVE LOGITS
    ]
    0.46
     مذکور
    0.44
    4
    0.43
    3
    0.41
    ],
    0.40
     aforementioned
    0.37
    他还
    0.36
     Fig
    0.36
    win
    0.36
    "},
    0.36
    Activations Density 0.043%

    No Known Activations