© 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-262K
    7. 92734
    Prev
    Next
    INDEX
    Explanations

    binary strings or data padding

    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_262k_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
     chopsticks
    0.51
     spoons
    0.48
    tsky
    0.48
     refugees
    0.47
     に
    0.46
     извест
    0.46
    ஜித்
    0.46
     capillaries
    0.45
     言
    0.45
     pillows
    0.45
    POSITIVE LOGITS
    碇
    0.42
    প্রতি
    0.41
    󠁣
    0.40
     retrofit
    0.39
    গত
    0.39
    ]=='
    0.39
    蚪
    0.39
    து
    0.39
    无论
    0.39
    '");
    0.39
    Activations Density 0.002%

    No Known Activations