© 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. 202925
    Prev
    Next
    INDEX
    Explanations

    LEGO blocks, devastating, impossibility, tied

    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
    棻
    0.48
    ニチイ
    0.47
    چہ
    0.47
    durch
    0.47
    を受
    0.47
    트를
    0.47
    ್ರಾ
    0.46
    Kelas
    0.46
    ydın
    0.46
    冫
    0.46
    POSITIVE LOGITS
     dangerous
    0.48
     बोलते
    0.47
     ridiculously
    0.47
     \
    0.46
     however
    0.46
     labs
    0.46
     we
    0.46
     boiling
    0.46
     cambiado
    0.46
     data
    0.45
    Activations Density 0.008%

    No Known Activations