© 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. 144262
    Prev
    Next
    INDEX
    Explanations

    short and straight

    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
    íř
    0.49
    ాయని
    0.48
    ittelt
    0.47
     стран
    0.47
    jetas
    0.46
    箖
    0.45
    пить
    0.45
    ímos
    0.44
     लेसन
    0.43
    ехать
    0.43
    POSITIVE LOGITS
     FL
    0.57
    m
    0.51
    0.50
     PAN
    0.48
     Tax
    0.47
     etk
    0.46
     mengatasi
    0.46
     origami
    0.45
     hae
    0.45
     classic
    0.45
    Activations Density 0.002%

    No Known Activations