© 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. 16-GEMMASCOPE-2-RES-262K
    7. 33880
    Prev
    Next
    INDEX
    Explanations

    going the extra mile

    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_16_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
     multiplicar
    0.60
    at
    0.57
    ни
    0.57
     Nazionale
    0.56
    ol
    0.55
     calda
    0.55
    રી
    0.54
    i
    0.54
    決して
    0.53
     flannel
    0.52
    POSITIVE LOGITS
     تط
    0.56
     ис
    0.54
    قدم
    0.53
    ه
    0.53
    خر
    0.52
     மறு
    0.52
    mos
    0.52
    要有
    0.51
     entscheid
    0.50
    قوم
    0.49
    Activations Density 0.000%

    No Known Activations