© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27024
    Prev
    Next
    INDEX
    Explanations

    technical procedures and results

    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
    akis
    0.43
    וח
    0.41
    к
    0.39
    另外
    0.39
     אם
    0.39
     دوم
    0.39
    نس
    0.38
    ὤ
    0.38
    대로
    0.38
     δεύτε
    0.36
    POSITIVE LOGITS
     lokalen
    0.49
     estre
    0.47
     शिक्षण
    0.47
     diperlukan
    0.45
     entornos
    0.44
     discos
    0.44
     regol
    0.43
     decryption
    0.43
     disco
    0.42
     crowded
    0.42
    Activations Density 0.001%

    No Known Activations