© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112371
    Prev
    Next
    INDEX
    Explanations

    rough estimate

    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
    тан
    0.51
    є
    0.49
    ление
    0.47
    ем
    0.45
    イズ
    0.45
     tidur
    0.44
    ит
    0.44
    ев
    0.44
    ень
    0.44
    冶
    0.42
    POSITIVE LOGITS
     أنها
    0.49
     osobe
    0.45
     họ
    0.44
     sowohl
    0.43
     Together
    0.43
     एलान
    0.41
     Configuring
    0.41
     अनुच्छेद
    0.41
     Ư
    0.40
     insieme
    0.40
    Activations Density 0.006%

    No Known Activations