© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 17465
    Prev
    Next
    INDEX
    Explanations

    artifact creation

    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
    ++.
    0.41
     жи
    0.39
    オ
    0.39
    वु
    0.39
    +.
    0.38
    дон
    0.38
     косми
    0.38
    뤽
    0.38
    超越
    0.37
    রাত
    0.36
    POSITIVE LOGITS
    為了
    0.47
     Parameters
    0.46
    unakan
    0.42
    வதற்காக
    0.41
     घेण्यासाठी
    0.40
     wikiHow
    0.39
     Voici
    0.39
     위해서는
    0.39
    redients
    0.39
     খুবই
    0.39
    Activations Density 0.005%

    No Known Activations