© 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. 111064
    Prev
    Next
    INDEX
    Explanations

    methods for practicing

    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
    윕
    0.45
     હશે
    0.45
    ούς
    0.44
    يكون
    0.44
     يكون
    0.43
    㴦
    0.43
    ар
    0.43
    rógeno
    0.43
     當
    0.43
     इक्
    0.42
    POSITIVE LOGITS
    s
    0.56
     zucchini
    0.54
    lg
    0.53
    x
    0.52
     myelin
    0.51
     orchid
    0.51
     podcast
    0.48
    ی
    0.48
     orchids
    0.48
     OPPO
    0.48
    Activations Density 0.002%

    No Known Activations