© 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. 138284
    Prev
    Next
    INDEX
    Explanations

    uniting disparate territories

    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
    冦
    0.54
    т
    0.51
    த்
    0.51
    ૩
    0.50
    Prothorax
    0.49
    п
    0.49
     музи
    0.48
     короб
    0.47
     études
    0.47
    ᱞ
    0.47
    POSITIVE LOGITS
     Knud
    0.45
     styled
    0.43
     UTS
    0.43
     quebr
    0.42
     city
    0.42
     Read
    0.42
     Spanish
    0.42
     Ø
    0.41
     Paulista
    0.41
     speckled
    0.41
    Activations Density 0.000%

    No Known Activations