© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 55349
    Prev
    Next
    INDEX
    Explanations

    content warnings and themes

    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_65k_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
    0.54
    6
    0.52
    8
    0.51
    奬
    0.50
    3
    0.49
    7
    0.49
    9
    0.49
    What
    0.46
    5
    0.46
    Note
    0.45
    POSITIVE LOGITS
     குறிப்பிட்ட
    0.48
    ऩ
    0.46
     giày
    0.44
     voller
    0.44
     außergewöhn
    0.44
     نفرت
    0.43
     fortal
    0.43
     kadın
    0.43
     چلا
    0.42
     falou
    0.42
    Activations Density 0.002%

    No Known Activations