© 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-16K
    7. 4365
    Prev
    Next
    INDEX
    Explanations

    taking actions or states

    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_16k_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
    りました
    0.55
    ச்சூழ
    0.55
     لوبو
    0.52
    URCH
    0.52
     செய்யப்பட்ட
    0.51
    3
    0.50
    úncia
    0.50
     AttributeError
    0.49
    〢
    0.49
    pré
    0.49
    POSITIVE LOGITS
     took
    0.96
     advantage
    0.91
     take
    0.84
     taken
    0.83
     TAKE
    0.79
     taking
    0.78
     Took
    0.78
     Take
    0.76
     Taking
    0.75
     care
    0.72
    Activations Density 0.151%

    No Known Activations